© 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. 9-RES-JB
    11. 16341
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the domain "co.uk" and associated URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numbering
    -0.73
    urally
    -0.68
    JUST
    -0.66
    Enlarge
    -0.61
     Revel
    -0.60
    ricular
    -0.59
     Gins
    -0.59
    entially
    -0.58
     GOODMAN
    -0.57
    Origin
    -0.57
    POSITIVE LOGITS
    ffee
    1.41
    legraph
    0.89
    zzle
    0.83
    verage
    0.83
    ven
    0.83
    pper
    0.82
    opers
    0.81
    ilers
    0.80
    ggles
    0.79
    perty
    0.79
    Activations Density 0.021%

    No Known Activations