© 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. 10-RES-JB
    11. 14186
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    statements and descriptive sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attrition
    -0.94
     casualty
    -0.87
     cessation
    -0.86
     boycot
    -0.86
     satell
    -0.85
     scheduling
    -0.84
     affili
    -0.84
     renegoti
    -0.84
     timely
    -0.84
     eligibility
    -0.83
    POSITIVE LOGITS
     Its
    1.37
     Notice
    1.33
     Each
    1.32
     Behind
    1.24
     It
    1.23
     Presumably
    1.23
     Inside
    1.22
     Interestingly
    1.21
     Somehow
    1.19
     Apparently
    1.18
    Activations Density 0.374%

    No Known Activations