© 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. 9-RES-JB
    11. 1325
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and investigations, such as "accuses" or "investigation"

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating connections or relationships in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ital
    -0.75
    banks
    -0.67
    ahime
    -0.66
    mos
    -0.65
    onne
    -0.64
    lems
    -0.63
    lights
    -0.63
    Offline
    -0.63
    agos
    -0.63
    olutions
    -0.62
    POSITIVE LOGITS
     Associates
    1.04
     others
    1.03
     his
    0.97
     Sons
    0.83
    ERSON
    0.80
     other
    0.78
     fellow
    0.76
     thereby
    0.73
     Others
    0.73
     her
    0.70
    Activations Density 0.183%

    No Known Activations