© 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. 11-RES-JB
    11. 7044
    Prev
    Next
    INDEX
    Explanations

    prices expressed in US dollars

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nomine
    -0.75
     commun
    -0.72
     clos
    -0.72
     unden
    -0.68
     backlog
    -0.67
     advis
    -0.65
     corridors
    -0.65
     quot
    -0.64
     dialect
    -0.63
    uyomi
    -0.62
    POSITIVE LOGITS
    299
    1.54
    199
    1.52
    399
    1.52
    499
    1.50
    599
    1.46
    349
    1.46
    149
    1.46
    699
    1.42
    179
    1.40
    899
    1.40
    Activations Density 0.054%

    No Known Activations