© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    proper names and mention of ranking

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and identifiers, particularly those associated with people or entities

    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
     Hayden
    -0.96
     Chin
    -0.94
     Ion
    -0.90
    Pan
    -0.89
     chin
    -0.85
     Paran
    -0.84
     Pan
    -0.84
     Kara
    -0.84
    chin
    -0.83
     Xan
    -0.80
    POSITIVE LOGITS
    alf
    1.57
    af
    1.41
     Af
    1.35
    uf
    1.21
     Alf
    1.20
    Af
    1.19
    AF
    1.18
    lf
    1.17
    EF
    1.17
     Haf
    1.15
    Activations Density 0.425%

    No Known Activations