© 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. 4-RES-JB
    11. 10091
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission or authorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enter" and its variations

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

    No Comments

    Negative Logits
    killer
    -0.79
    ector
    -0.71
     Archangel
    -0.69
    axter
    -0.64
    killers
    -0.62
    roxy
    -0.61
    killing
    -0.61
     gunned
    -0.61
     backdrop
    -0.60
    pedia
    -0.59
    POSITIVE LOGITS
    prising
    1.14
    prise
    1.14
    prises
    1.09
    apore
    0.88
    tainment
    0.81
    ococ
    0.73
    ATURE
    0.72
    tain
    0.72
    igmatic
    0.72
    ATURES
    0.71
    Activations Density 0.019%

    No Known Activations