© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7841
    Prev
    Next
    INDEX
    Explanations

    locations or specific places

    oai_token-act-pair · gpt-3.5-turbo

    phrases and references related to media, such as television shows and performances

    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
    encers
    -0.78
    encer
    -0.69
    ibur
    -0.69
    ritis
    -0.68
    upon
    -0.67
    ifax
    -0.66
    haar
    -0.66
    anmar
    -0.66
    blers
    -0.65
    ocate
    -0.65
    POSITIVE LOGITS
     occasions
    1.14
     basis
    1.00
     behalf
    1.00
     occasion
    0.84
     eve
    0.82
     footing
    0.79
     grounds
    0.77
     pretext
    0.76
     forums
    0.73
     fronts
    0.72
    Activations Density 0.973%

    No Known Activations