© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15845
    Prev
    Next
    INDEX
    Explanations

    details regarding a specific person's involvement in events or situations

    oai_token-act-pair · gpt-3.5-turbo

    content related to ongoing police investigations or inquiries

    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
     whilst
    -0.67
    estern
    -0.64
     tremend
    -0.59
     Whilst
    -0.58
     GREAT
    -0.56
     wonderful
    -0.56
     partName
    -0.55
     lovely
    -0.54
     fucking
    -0.54
     wonderfully
    -0.54
    POSITIVE LOGITS
     theirs
    0.73
     lawmaker
    0.66
     staffers
    0.65
    .).
    0.63
    ]."
    0.59
    >.
    0.58
    ongo
    0.58
    />
    0.57
    dozen
    0.57
    .''.
    0.57
    Activations Density 1.473%

    No Known Activations