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

    Neuronpedia

    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. 4-RES-JB
    11. 7364
    Prev
    Next
    INDEX
    Explanations

    references to sources, potentially citations or footnotes

    oai_token-act-pair · gpt-3.5-turbo

    formatted text or structures within the document

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

    No Comments

    Negative Logits
    oor
    -0.80
    ãĤ©
    -0.77
    ãĥ¼ãĥ³
    -0.71
    ient
    -0.71
    æ©
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    çīĪ
    -0.67
    ãĤ£
    -0.67
    é¾įå
    -0.67
    POSITIVE LOGITS
    ...]
    1.43
    âĢ¦]
    1.23
    ?]
    0.99
    ][
    0.91
    Pg
    0.90
    .]
    0.88
    ].
    0.87
     ][
    0.86
     ]
    0.86
    !]
    0.85
    Activations Density 0.021%

    No Known Activations