© 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. 1-RES-JB
    11. 8651
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific institutions or entities, particularly those containing the word "College"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly with the name "Gou" and variants related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barkley
    -0.86
    Ö¼
    -0.77
    abil
    -0.74
    sburgh
    -0.74
    arlane
    -0.72
    idency
    -0.71
    nyder
    -0.71
     à¤
    -0.70
    APS
    -0.69
    266
    -0.69
    POSITIVE LOGITS
     Kou
    1.13
    vernment
    1.07
    seless
    0.98
    hou
    0.98
    pload
    0.92
    vel
    0.92
    isine
    0.89
    raviolet
    0.86
     Jou
    0.83
    fman
    0.82
    Activations Density 0.013%

    No Known Activations