Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 15275
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to technology products, particularly focusing on audio, climate control, and steering features

    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
    1222
    +0.24
    1.3%
    172
    +0.14
    0.8%
    1806
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.24
    0.05
    1222
    +0.14
    0.04
    690
    +0.13
    0.04
    Negative Logits
     intersper
    -1.10
     apprehen
    -1.08
     encomp
    -0.95
     unve
    -0.92
     accla
    -0.91
     unspeak
    -0.89
     impelled
    -0.88
     reluct
    -0.86
     Mlle
    -0.85
     ineffec
    -0.85
    POSITIVE LOGITS
     til
    0.93
     Til
    0.90
    Til
    0.87
    til
    0.86
     Sid
    0.84
     Till
    0.83
     till
    0.78
    Till
    0.78
    TIL
    0.76
    Sid
    0.76
    Activations Density 0.529%

    No Known Activations