© 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. 6-RES-JB
    11. 18453
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and abbreviations related to specific identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rar
    -0.63
     Amend
    -0.61
     Pruitt
    -0.61
    Nik
    -0.60
    rade
    -0.59
     Garner
    -0.59
    mat
    -0.59
    aved
    -0.58
     Stephens
    -0.58
    rez
    -0.58
    POSITIVE LOGITS
     itself
    0.79
     inhibitors
    0.70
     Syndrome
    0.66
     Citadel
    0.61
     syndrome
    0.60
     bandwagon
    0.59
     herself
    0.58
    's
    0.57
     Implementation
    0.57
     aloud
    0.57
    Activations Density 0.412%

    No Known Activations