© 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. 2739
    Prev
    Next
    INDEX
    Explanations

    strong action verbs or impactful words

    oai_token-act-pair · gpt-3.5-turbo

    strong action verbs and phrases related to commands or significant actions

    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
    issance
    -0.67
    iscons
    -0.65
     COURT
    -0.65
     enthusi
    -0.64
     destro
    -0.63
     agre
    -0.63
    ammy
    -0.61
     encount
    -0.61
     Ange
    -0.58
    Cub
    -0.57
    POSITIVE LOGITS
    ingly
    1.01
    ings
    0.99
    eth
    0.86
    fully
    0.85
     themselves
    0.84
    adelphia
    0.80
    ned
    0.78
    ably
    0.74
    ively
    0.72
    ories
    0.72
    Activations Density 0.574%

    No Known Activations