© 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. 8-RES-JB
    11. 20234
    Prev
    Next
    INDEX
    Explanations

    descriptions related to parts of a structure, likely a technical document

    oai_token-act-pair · gpt-3.5-turbo

    specific references to military or governmental entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }.
    -0.72
    .).
    -0.71
     UNCLASSIFIED
    -0.71
    )).
    -0.69
    Advertisements
    -0.67
    )."
    -0.67
    anwhile
    -0.66
    ]).
    -0.65
    +.
    -0.64
     destro
    -0.63
    POSITIVE LOGITS
    ikarp
    0.58
     âĢİ
    0.54
    ÂŃ
    0.54
     Donald
    0.53
     Mana
    0.53
    Äģ
    0.52
    Islam
    0.51
    onnaissance
    0.51
     hockey
    0.50
    Åį
    0.50
    Activations Density 0.831%

    No Known Activations