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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8376
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements related to length

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1385
    +0.12
    0.4%
    86
    +0.10
    0.3%
    36
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.03
    1110
    +0.10
    0.03
    1705
    +0.10
    0.03
    Negative Logits
     squa
    -1.37
     fortn
    -1.37
     secon
    -1.34
     volunte
    -1.31
     encomp
    -1.31
     affor
    -1.27
     reluct
    -1.26
     oner
    -1.26
     increa
    -1.24
     tew
    -1.23
    POSITIVE LOGITS
     inches
    0.99
     inch
    0.95
    inch
    0.81
    inches
    0.79
     diameter
    0.75
     width
    0.69
     height
    0.66
     thickness
    0.63
     size
    0.60
     feet
    0.60
    Activations Density 0.085%

    No Known Activations