© 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. 0-RES-JB
    11. 1159
    Prev
    Next
    INDEX
    Explanations

    words related to mirrors or reflection

    oai_token-act-pair · gpt-3.5-turbo

    words related to horror or terror themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plantation
    -0.65
     conqu
    -0.64
     tamp
    -0.64
     matters
    -0.60
     plants
    -0.60
     Sugar
    -0.60
     plantations
    -0.59
     Hath
    -0.59
     sweet
    -0.58
     consumed
    -0.57
    POSITIVE LOGITS
    ror
    4.92
    rors
    2.52
    ROR
    2.03
    rored
    1.89
    rote
    1.21
    rones
    1.07
    ron
    1.06
    acle
    1.06
    ral
    1.05
    rent
    1.03
    Activations Density 0.013%

    No Known Activations