© 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. 13411
    Prev
    Next
    INDEX
    Explanations

    website or social media features like login/sign-up prompts

    oai_token-act-pair · gpt-3.5-turbo

    vertical bars or pipe characters ("|")

    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
    alis
    -0.84
    anium
    -0.80
    anski
    -0.79
    rons
    -0.78
    ifts
    -0.77
    ory
    -0.77
    ypes
    -0.75
    chenko
    -0.74
    esi
    -0.73
    orical
    -0.72
    POSITIVE LOGITS
    cffff
    1.10
     |--
    0.89
    ··
    0.88
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.75
    cffffcc
    0.74
    ————
    0.72
    ¯¯¯¯¯¯¯¯
    0.71
     +---
    0.71
    âĢ¢âĢ¢
    0.71
     grep
    0.71
    Activations Density 0.021%

    No Known Activations