© 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. 4-RES-JB
    11. 15209
    Prev
    Next
    INDEX
    Explanations

    the word "Sham" with varying degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sham" and related variations

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

    No Comments

    Negative Logits
    lihood
    -0.72
     Gerry
    -0.69
    ĸļ
    -0.68
     Hawking
    -0.63
     Wiley
    -0.63
    IBLE
    -0.63
     newsletters
    -0.62
     compounded
    -0.62
    PsyNetMessage
    -0.61
     Suns
    -0.60
    POSITIVE LOGITS
    eless
    1.26
    rock
    1.14
    blers
    1.12
    Sham
    0.99
    aji
    0.98
    rod
    0.91
    arie
    0.89
    anyahu
    0.88
    ory
    0.88
    ash
    0.87
    Activations Density 0.011%

    No Known Activations