© 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. 0-RES-JB
    11. 3753
    Prev
    Next
    INDEX
    Explanations

    keywords related to software development tools and versions

    oai_token-act-pair · gpt-3.5-turbo

    references to beta testing and software frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olson
    -0.80
    cedes
    -0.78
     rand
    -0.78
     maneuver
    -0.75
     lyr
    -0.72
     manoeuv
    -0.72
     outl
    -0.71
     pil
    -0.71
     ride
    -0.70
     rhy
    -0.69
    POSITIVE LOGITS
     Beta
    2.40
     Framework
    1.99
     Preview
    1.54
    Beta
    1.45
     Guides
    1.21
     Gamma
    1.20
     Directive
    1.18
     Lic
    1.17
     License
    1.06
     Guide
    1.06
    Activations Density 0.033%

    No Known Activations