© 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. 8308
    Prev
    Next
    INDEX
    Explanations

    the name "Kesler"

    oai_token-act-pair · gpt-3.5-turbo
    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
    itton
    -0.76
    head
    -0.75
    heads
    -0.72
     RIGHT
    -0.70
     jackets
    -0.70
    acent
    -0.69
     Else
    -0.67
     Malf
    -0.67
     ado
    -0.66
     Mob
    -0.66
    POSITIVE LOGITS
    llers
    0.84
    amel
    0.84
    ller
    0.80
    earchers
    0.77
    pal
    0.75
    brates
    0.74
    wered
    0.74
    brate
    0.74
    rers
    0.73
    gel
    0.73
    Activations Density 0.021%

    No Known Activations