© 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. 8-RES-JB
    11. 848
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating hidden or secret locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating hidden or underlying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onite
    -0.70
    won
    -0.68
    amen
    -0.67
    usercontent
    -0.65
    assic
    -0.63
    rouse
    -0.61
    udes
    -0.60
    ennes
    -0.59
     trespass
    -0.59
     vulner
    -0.58
    POSITIVE LOGITS
    neath
    0.90
     Scenes
    0.76
    bek
    0.69
    stellar
    0.67
    VIEW
    0.67
    words
    0.65
     Features
    0.65
    word
    0.65
     conclud
    0.65
     Stories
    0.64
    Activations Density 0.219%

    No Known Activations