© 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. 16951
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or combination of elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical data and analysis

    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
    insk
    -0.74
    ICAN
    -0.71
    PRES
    -0.69
    ciation
    -0.68
    ans
    -0.68
    anners
    -0.67
    ANS
    -0.64
     ({
    -0.64
    rone
    -0.64
    versible
    -0.60
    POSITIVE LOGITS
     fact
    0.77
     unbeliev
    0.74
     inexper
    0.74
    ãĥ¼ãĥĨãĤ£
    0.73
     sheer
    0.73
    juries
    0.70
     anecd
    0.69
     impro
    0.69
    itivity
    0.67
     incompetence
    0.66
    Activations Density 0.116%

    No Known Activations