© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1172
    Prev
    Next
    INDEX
    Explanations

    keywords related to counseling and mental health services

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1047
    +0.19
    1.0%
    938
    +0.13
    0.6%
    1065
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.19
    0.03
    1363
    +0.13
    0.02
    1026
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.15
    ⓧ
    -0.56
     gouvernements
    -0.56
    HasIndex
    -0.54
    leg
    -0.53
    glLoadIdentity
    -0.53
    static
    -0.51
    transform
    -0.49
     become
    -0.49
     dis
    -0.48
    POSITIVE LOGITS
     COUNSEL
    1.36
     counseling
    1.29
     counselor
    1.29
    coun
    1.28
     Counsel
    1.27
     Counseling
    1.27
     counselors
    1.26
    Coun
    1.25
     counselling
    1.20
     counsel
    1.20
    Activations Density 0.214%

    No Known Activations