© 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. 24003
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of scrapping or getting rid of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "scrapping" or discarding items or ideas

    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
    CVE
    -0.80
    igmatic
    -0.74
    secut
    -0.73
    annis
    -0.72
    ocytes
    -0.70
    ocent
    -0.69
     guilty
    -0.69
    secution
    -0.68
    culus
    -0.67
     complicit
    -0.67
    POSITIVE LOGITS
     scrap
    0.92
    yard
    0.91
    hire
    0.88
     scraps
    0.87
    ãĤ¡
    0.86
    bones
    0.85
     shred
    0.82
    yards
    0.82
    dump
    0.81
    enhagen
    0.80
    Activations Density 0.009%

    No Known Activations