© 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. 18479
    Prev
    Next
    INDEX
    Explanations

    actions or operations being carried out

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "carried out."

    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
    esa
    -0.64
    icago
    -0.61
    bucks
    -0.61
    gdala
    -0.61
    posure
    -0.59
    stadt
    -0.56
    bies
    -0.55
    ractions
    -0.55
     vandal
    -0.55
     hex
    -0.53
    POSITIVE LOGITS
    forward
    0.83
    out
    0.80
    ued
    0.73
    IGH
    0.73
    weight
    0.70
    ĸļ
    0.70
    jriwal
    0.69
    rower
    0.67
     forward
    0.67
    aways
    0.65
    Activations Density 0.026%

    No Known Activations