© 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. 23988
    Prev
    Next
    INDEX
    Explanations

    words related to mirrors and reflections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to horror

    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
    xxxxxxxx
    -0.70
    doi
    -0.66
    mable
    -0.64
    enery
    -0.63
     Carth
    -0.63
    Fra
    -0.63
     Calories
    -0.62
    Ī
    -0.61
     Vi
    -0.61
    æ©
    -0.61
    POSITIVE LOGITS
    ror
    1.73
    etheless
    1.05
    ROR
    0.92
    rors
    0.92
    hin
    0.83
    cffff
    0.82
    terday
    0.80
     guiActiveUn
    0.79
    adeon
    0.78
    bably
    0.77
    Activations Density 0.011%

    No Known Activations