© 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. 4-RES-JB
    11. 14855
    Prev
    Next
    INDEX
    Explanations

    emojis

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols

    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
     Gillespie
    -0.85
     Manit
    -0.76
     Akin
    -0.72
    wagen
    -0.71
     Sakuya
    -0.70
     Bain
    -0.69
     Abyssal
    -0.67
     Samson
    -0.67
     Whitman
    -0.67
     Sidd
    -0.67
    POSITIVE LOGITS
    ¥ŀ
    1.30
    ĻĤ
    1.25
    Ķ
    1.24
    ĵ
    1.23
    ĵĺ
    1.20
    ðŁ
    1.20
    Ĵ
    1.17
    į
    1.13
    Į
    1.12
    İ
    1.08
    Activations Density 0.004%

    No Known Activations