© 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. 21385
    Prev
    Next
    INDEX
    Explanations

    internet-related terms such as websites and online activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complex systems and their interaction with society

    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
    atorium
    -0.72
    amaz
    -0.68
    REDACTED
    -0.64
    aeper
    -0.60
    ãĥ£
    -0.59
    ACTED
    -0.59
    CHAT
    -0.59
    same
    -0.58
    iversary
    -0.58
    ãĤ©
    -0.58
    POSITIVE LOGITS
    paces
    1.31
    hips
    1.20
     such
    1.04
    pace
    1.04
    hip
    0.97
     like
    0.95
    mith
    0.93
    ets
    0.92
    poons
    0.90
    manship
    0.89
    Activations Density 0.563%

    No Known Activations