© 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. 10-RES-JB
    11. 17399
    Prev
    Next
    INDEX
    Explanations

    references to citations or sources within text

    oai_token-act-pair · gpt-3.5-turbo

    references to citations

    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
    inav
    -0.88
    pora
    -0.74
    merce
    -0.71
    ratulations
    -0.69
    milo
    -0.68
    Jet
    -0.65
    FTWARE
    -0.65
    sburg
    -0.61
    steen
    -0.61
    wear
    -0.60
    POSITIVE LOGITS
     omitted
    1.00
    ]"
    0.92
    =]
    0.91
     needed
    0.91
    ][
    0.89
    ]
    0.84
    ])
    0.83
    ?]
    0.83
    ]).
    0.81
    ],[
    0.79
    Activations Density 0.020%

    No Known Activations