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

    Neuronpedia

    APICircuit 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. 408
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and renovation projects

    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
    1438
    +0.15
    0.7%
    1150
    +0.15
    0.7%
    2034
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.15
    0.25
    2034
    +0.15
    0.21
    1438
    +0.14
    0.13
    Negative Logits
    <bos>
    -3.70
     intersper
    -2.10
     fuf
    -1.89
     encomp
    -1.82
     increa
    -1.81
     emphat
    -1.81
     inconce
    -1.71
     reluct
    -1.67
     disagre
    -1.65
     purcha
    -1.64
    POSITIVE LOGITS
    .
    0.93
    :].
    0.87
    ]=="
    0.86
    。
    0.82
    ।
    0.80
    .‏
    0.80
     ।
    0.78
    ."\
    0.78
    VELOP
    0.78
    atiable
    0.76
    Activations Density 6.307%

    No Known Activations