© 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. 2-RES-JB
    11. 4360
    Prev
    Next
    INDEX
    Explanations

    nouns related to recreational activities and substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entertainment and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iggins
    -0.79
    yssey
    -0.76
    lez
    -0.72
    awks
    -0.72
    aves
    -0.72
    onds
    -0.71
    encer
    -0.71
    iott
    -0.70
    awk
    -0.69
    yne
    -0.69
    POSITIVE LOGITS
     Corpus
    0.90
     amusement
    0.87
    ptive
    0.85
    ptives
    0.82
     consolation
    0.80
     concession
    0.77
    ¿½
    0.70
    ilial
    0.67
    esan
    0.66
    piece
    0.65
    Activations Density 0.015%

    No Known Activations