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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12995
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking individuals or services for particular roles or needs

    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
    429
    +0.09
    0.2%
    1459
    +0.08
    0.2%
    1745
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2045
    +0.09
    0.05
    1745
    +0.08
    0.04
    773
    +0.07
    0.04
    Negative Logits
     increa
    -1.41
     maneu
    -1.38
     ?...
    -1.36
     alre
    -1.33
     Juf
    -1.31
     !...
    -1.27
     effe
    -1.26
     fuf
    -1.25
     erad
    -1.25
     squa
    -1.24
    POSITIVE LOGITS
     capable
    0.69
     PeEnEo
    0.69
    <bos>
    0.67
     urgently
    0.66
     someone
    0.66
     suitable
    0.63
     preferably
    0.62
     to
    0.61
     something
    0.60
     willing
    0.60
    Activations Density 0.471%

    No Known Activations