© 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. 5083
    Prev
    Next
    INDEX
    Explanations

    Greek and Turkish male names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Afa" and its variations in different 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
    lust
    -0.88
    lines
    -0.82
    lined
    -0.73
    matic
    -0.69
    bone
    -0.68
    suit
    -0.68
    rigan
    -0.67
    line
    -0.67
    nces
    -0.65
    tle
    -0.65
    POSITIVE LOGITS
    ña
    1.00
    qua
    0.97
    ÄŁ
    0.97
    ÅĤ
    0.97
    ça
    0.88
    ñ
    0.88
    afa
    0.84
    ı
    0.83
    ÅŁ
    0.82
    qs
    0.81
    Activations Density 0.010%

    No Known Activations