© 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. 10311
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Blanche" in various contexts

    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
    olved
    -0.79
    iating
    -0.78
    APS
    -0.76
    owment
    -0.70
    iates
    -0.69
    iated
    -0.68
    adic
    -0.67
    iage
    -0.66
    ICES
    -0.65
    ensible
    -0.64
    POSITIVE LOGITS
    tta
    0.94
    xual
    0.94
    zza
    0.93
    ttes
    0.93
    tti
    0.89
    eers
    0.89
    esome
    0.87
    stals
    0.83
    erness
    0.80
     Hebdo
    0.80
    Activations Density 0.012%

    No Known Activations