© 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. 13585
    Prev
    Next
    INDEX
    Explanations

    food-related items

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the conjunction "and" that link various elements or ideas together

    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
    lems
    -0.91
    Ĥİ
    -0.87
    psc
    -0.86
    pees
    -0.80
    MET
    -0.77
    MU
    -0.74
    YP
    -0.74
    pes
    -0.73
    ships
    -0.72
    nces
    -0.71
    POSITIVE LOGITS
     then
    0.88
     therefore
    0.88
     consequently
    0.87
     subsequent
    0.82
     hence
    0.81
     thus
    0.78
     THEN
    0.78
     subsequently
    0.77
     thats
    0.76
     secondly
    0.76
    Activations Density 0.316%

    No Known Activations