© 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. 6414
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    references to "Confederate" themes or topics

    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
    senal
    -1.04
    OHN
    -0.77
    BALL
    -0.73
    BuyableInstoreAndOnline
    -0.72
    minecraft
    -0.70
    fare
    -0.69
    mes
    -0.68
    ENA
    -0.68
    tis
    -0.67
    matically
    -0.67
    POSITIVE LOGITS
    irmation
    1.54
    idential
    1.47
    licts
    1.44
    lict
    1.43
    irmed
    1.37
    irms
    1.33
    licted
    1.32
    irming
    1.32
    luence
    1.22
    erences
    1.18
    Activations Density 0.032%

    No Known Activations