© 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. 18739
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions involving movement and objects

    oai_token-act-pair · gpt-3.5-turbo

    metaphors and similes related to experiences and concepts

    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
    POSE
    -0.84
    CLASSIFIED
    -0.83
    Materials
    -0.80
    ODUCT
    -0.74
    METHOD
    -0.74
    ANC
    -0.73
    ETHOD
    -0.72
    HC
    -0.71
    cellaneous
    -0.71
     INFORMATION
    -0.71
    POSITIVE LOGITS
     nap
    0.93
     fries
    0.91
     potato
    0.90
     torches
    0.85
     popcorn
    0.85
     pillow
    0.84
     aspirin
    0.84
     peanuts
    0.82
     Doodle
    0.82
     tin
    0.81
    Activations Density 1.709%

    No Known Activations