© 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. 4-RES-JB
    11. 9124
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related markers

    oai_token-act-pair · gpt-3.5-turbo

    HTML/XML-like tags and attributes related to data formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    duction
    -0.86
    女
    -0.69
    Ĥª
    -0.68
    mails
    -0.68
    ãģ®éŃĶ
    -0.68
     reconc
    -0.67
    zona
    -0.66
    tained
    -0.66
    keeping
    -0.65
    ptives
    -0.65
    POSITIVE LOGITS
    uner
    0.96
    imore
    0.90
    arkin
    0.90
    ogether
    0.88
    imes
    0.82
    ucket
    0.81
    itudinal
    0.79
    itle
    0.79
    itude
    0.78
    sson
    0.76
    Activations Density 0.009%

    No Known Activations