© 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. 6-RES-JB
    11. 11737
    Prev
    Next
    INDEX
    Explanations

    specific names

    oai_token-act-pair · gpt-3.5-turbo

    empty sections or the end of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arms
    -0.98
    erie
    -0.88
    ī
    -0.79
    Ģ
    -0.79
    antine
    -0.78
    Ĵ
    -0.75
    rum
    -0.73
    atable
    -0.73
    ģ
    -0.71
    rations
    -0.71
    POSITIVE LOGITS
    vironment
    0.99
    FFER
    0.79
    elson
    0.78
    linger
    0.77
    viron
    0.71
    BIL
    0.69
    hee
    0.69
    CRIP
    0.67
    esis
    0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.66
    Activations Density 0.067%

    No Known Activations