© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    words related to something that has an end or completion

    oai_token-act-pair · gpt-3.5-turbo

    words that end with a specific suffix

    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
    ppo
    -0.75
    veland
    -0.75
    apo
    -0.71
    anca
    -0.65
    edom
    -0.65
    issance
    -0.65
    ched
    -0.65
    alog
    -0.63
    ching
    -0.62
    thood
    -0.61
    POSITIVE LOGITS
    ending
    1.01
    ends
    0.95
    ended
    0.90
    ENDED
    0.82
    lich
    0.80
    END
    0.72
    rils
    0.71
    end
    0.71
    End
    0.70
    ĸļ
    0.68
    Activations Density 0.015%

    No Known Activations