© 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. 13465
    Prev
    Next
    INDEX
    Explanations

    words related to causing physical harm or damage

    oai_token-act-pair · gpt-3.5-turbo

    action words indicating processes or activities

    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
    ULTS
    -0.68
    cius
    -0.64
     ACTION
    -0.63
    aimon
    -0.61
     Pwr
    -0.61
     Nare
    -0.59
     sidx
    -0.59
     Harlem
    -0.56
     brim
    -0.56
    Ear
    -0.55
    POSITIVE LOGITS
    ing
    2.70
    ership
    1.29
    ING
    1.28
    ments
    1.25
    ging
    1.25
    ingham
    1.24
    eering
    1.24
    edIn
    1.21
    ingly
    1.20
    ning
    1.13
    Activations Density 0.237%

    No Known Activations