© 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. 7-RES-JB
    11. 17213
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical instructions or coding languages

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eny
    -0.60
    agin
    -0.60
    anto
    -0.59
    venture
    -0.59
    iant
    -0.58
     Fortune
    -0.56
    leground
    -0.55
     ubiquitous
    -0.54
    fortune
    -0.53
    meric
    -0.52
    POSITIVE LOGITS
     Hammond
    0.59
    verty
    0.59
     itself
    0.59
    ]),
    0.59
    ]);
    0.58
     reper
    0.55
     FIA
    0.54
    Forge
    0.53
     scrimmage
    0.53
    ]).
    0.53
    Activations Density 1.255%

    No Known Activations