© 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. 10-RES-JB
    11. 5354
    Prev
    Next
    INDEX
    Explanations

    phrases describing conflict or confrontation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and their impact or usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.52
    isSpecialOrderable
    -0.43
    famous
    -0.42
    thood
    -0.42
    NAS
    -0.41
    masters
    -0.40
    Ü
    -0.40
    omach
    -0.39
    ocrates
    -0.39
    Year
    -0.39
    POSITIVE LOGITS
    '."
    0.44
    .'"
    0.43
     respectively
    0.43
    ]."
    0.43
    )."
    0.42
     Extras
    0.39
     };
    0.39
     cann
    0.39
    }"
    0.38
     leveraging
    0.36
    Activations Density 1.941%

    No Known Activations