© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 20259
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities that involve a group or team

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "setups" or structured arrangements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veget
    -0.67
    qus
    -0.66
     vel
    -0.64
    isks
    -0.63
     monk
    -0.61
     lucid
    -0.61
    ¯
    -0.59
     Lanka
    -0.58
     unde
    -0.57
     tc
    -0.57
    POSITIVE LOGITS
    sized
    1.02
    changing
    0.97
    length
    0.96
    based
    0.96
    footed
    0.95
    setting
    0.91
    of
    0.91
    level
    0.91
    wise
    0.91
    record
    0.90
    Activations Density 0.099%

    No Known Activations