© 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. 8-RES-JB
    11. 18700
    Prev
    Next
    INDEX
    Explanations

    specific characters or character configurations

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or corrupted text characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fortun
    -0.84
     intersect
    -0.76
     mathemat
    -0.75
     pooled
    -0.73
     synerg
    -0.70
     yield
    -0.69
     fuse
    -0.69
     dispers
    -0.69
     variance
    -0.68
     aggreg
    -0.68
    POSITIVE LOGITS
    ship
    0.99
    ï¸ı
    0.98
    sic
    0.93
    tal
    0.93
    ski
    0.92
    ember
    0.89
    Wilson
    0.87
    mas
    0.84
    iversary
    0.83
    tis
    0.81
    Activations Density 0.236%

    No Known Activations