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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2591
    Prev
    Next
    INDEX
    Explanations

    statements about potential changes or decisions being made within a specific context

    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
    509
    +0.10
    0.3%
    674
    +0.08
    0.2%
    1042
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1289
    +0.10
    0.04
    315
    +0.08
    0.04
    509
    +0.08
    0.04
    Negative Logits
     increa
    -1.32
     effe
    -1.26
     aen
    -1.26
     guarante
    -1.25
     erad
    -1.22
     impra
    -1.21
     scrat
    -1.17
     fta
    -1.15
     erec
    -1.15
     affor
    -1.14
    POSITIVE LOGITS
     replacement
    0.95
     replacements
    0.89
     successor
    0.76
     replace
    0.76
     Replacement
    0.74
     replaced
    0.73
     replacing
    0.69
     succession
    0.64
    replacement
    0.64
     newOwner
    0.63
    Activations Density 0.392%

    No Known Activations