© 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. 10057
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming or encryption file formats

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or patterns in words

    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
     mathemat
    -0.80
    ammy
    -0.75
     fortun
    -0.74
     elig
    -0.68
     contrace
    -0.68
     misunder
    -0.66
    omorphic
    -0.65
     assum
    -0.64
    aimon
    -0.64
    wana
    -0.64
    POSITIVE LOGITS
    ï¸ı
    0.79
    ½
    0.76
    ï¸
    0.74
     istg
    0.74
    audi
    0.74
    hall
    0.73
    âĹ¼
    0.70
    £
    0.69
    Balt
    0.68
    ¯¯¯¯
    0.68
    Activations Density 0.415%

    No Known Activations