© 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. 7-RES-JB
    11. 11643
    Prev
    Next
    INDEX
    Explanations

    places where users are prompted to input information like email addresses or codes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user actions and inputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Panther
    -0.72
    utsche
    -0.69
    lance
    -0.66
    fml
    -0.66
    hawk
    -0.60
     Tycoon
    -0.60
    die
    -0.60
     Telecom
    -0.59
     Bears
    -0.59
    FH
    -0.58
    POSITIVE LOGITS
    prising
    1.13
    prise
    1.11
    prises
    1.07
    tainment
    0.97
    tain
    0.92
    tained
    0.83
    taining
    0.81
    leep
    0.78
    ococ
    0.73
     captcha
    0.72
    Activations Density 0.020%

    No Known Activations