Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10998
    Prev
    Next
    INDEX
    Explanations

    prepositions used in combination with action verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or dependent relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ryu
    -0.95
    thood
    -0.77
    erson
    -0.74
     Liberties
    -0.69
    odox
    -0.68
    listed
    -0.66
    ãģ«
    -0.65
    encer
    -0.65
    eson
    -0.65
    istani
    -0.64
    POSITIVE LOGITS
     seams
    1.30
     edges
    0.85
     cracks
    0.79
     fumes
    0.78
     uncontroll
    0.75
     sudden
    0.73
     exhaustion
    0.72
     ankles
    0.72
     acidic
    0.71
     incompetence
    0.71
    Activations Density 0.442%

    No Known Activations