© 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. 7-RES-JB
    11. 20028
    Prev
    Next
    INDEX
    Explanations

    phrases related to accessibility or being easily reached

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acci
    -0.75
    conn
    -0.70
    erker
    -0.67
    osit
    -0.66
    ortium
    -0.65
    set
    -0.63
    oult
    -0.62
    cham
    -0.61
    hon
    -0.61
    sterdam
    -0.61
    POSITIVE LOGITS
    ibility
    1.06
    ible
    1.04
    ibly
    0.90
    isable
    0.77
     accessible
    0.73
    accessible
    0.71
    atable
    0.68
     centr
    0.68
     truths
    0.68
    DOS
    0.66
    Activations Density 0.038%

    No Known Activations