© 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. 18752
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations and locations of organizations

    oai_token-act-pair · gpt-3.5-turbo

    activities or events related to organizational changes or movements

    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
    ecd
    -0.75
    EStream
    -0.73
    entimes
    -0.69
    icious
    -0.65
    glers
    -0.65
    atio
    -0.64
     firsthand
    -0.63
    ilege
    -0.63
    "/>
    -0.63
     deprivation
    -0.62
    POSITIVE LOGITS
     Belfast
    0.75
     headquarters
    0.73
     USL
    0.70
     theaters
    0.68
     NHS
    0.68
     £
    0.67
     redevelopment
    0.66
     bankruptcy
    0.64
     downtown
    0.63
     revamped
    0.63
    Activations Density 0.910%

    No Known Activations