© 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. 20247
    Prev
    Next
    INDEX
    Explanations

    complex concepts or structures

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to complexity

    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
    OIL
    -0.75
    ï¸
    -0.72
    §
    -0.69
    ablishment
    -0.69
    ĵ
    -0.68
    HI
    -0.67
    baugh
    -0.66
    Ĭ±
    -0.64
    IGH
    -0.63
    Ķ
    -0.63
    POSITIVE LOGITS
    ioned
    1.21
    mble
    0.85
    lly
    0.82
    ions
    0.80
    ively
    0.79
    ly
    0.78
     configurations
    0.77
     layered
    0.76
     structured
    0.75
     logistical
    0.74
    Activations Density 0.044%

    No Known Activations