© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    terms related to resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resources and their management

    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
    arella
    -0.80
    deals
    -0.76
    ker
    -0.74
    alone
    -0.73
    erella
    -0.72
    ŃĶ
    -0.71
    ership
    -0.69
    lihood
    -0.68
    olini
    -0.64
     dece
    -0.64
    POSITIVE LOGITS
     resources
    1.00
    fulness
    0.97
    ourcing
    0.85
     allocation
    0.84
    available
    0.84
     expended
    0.79
    ourced
    0.78
     Sharing
    0.77
    ful
    0.76
     utilization
    0.75
    Activations Density 0.042%

    No Known Activations