© 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. 3713
    Prev
    Next
    INDEX
    Explanations

    words related to biases and cognitive tendencies

    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
    674
    +0.13
    0.4%
    872
    +0.11
    0.3%
    198
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    691
    +0.13
    0.01
    73
    +0.11
    0.02
    1923
    +0.09
    0.04
    Negative Logits
     reluct
    -1.23
     unlaw
    -1.22
     apprehen
    -1.18
     shenan
    -1.18
     disagre
    -1.17
     McLaugh
    -1.12
     pamph
    -1.10
     uninten
    -1.07
     sophistic
    -1.05
     impractica
    -1.05
    POSITIVE LOGITS
     Bourgoin
    0.59
    <bos>
    0.58
     OMIT
    0.56
     externi
    0.52
    RESULTADOS
    0.52
     actionMode
    0.52
    Segoe
    0.51
     gawas
    0.51
     convenient
    0.50
     Wasch
    0.50
    Activations Density 0.356%

    No Known Activations