© 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. 6-RES-JB
    11. 20275
    Prev
    Next
    INDEX
    Explanations

    locations or objects that are lost or missing

    oai_token-act-pair · gpt-3.5-turbo

    references to missing people, objects, or historical relics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.81
    natureconservancy
    -0.76
    ROR
    -0.74
    verning
    -0.73
    eu
    -0.73
    soDeliveryDate
    -0.71
    iscopal
    -0.70
    assadors
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
    tf
    -0.67
    POSITIVE LOGITS
     syndrome
    1.05
     Syndrome
    0.84
     carc
    0.71
     corpse
    0.69
     clinging
    0.67
    bris
    0.63
    mur
    0.63
     decom
    0.61
     corpses
    0.61
     streaks
    0.60
    Activations Density 0.315%

    No Known Activations