© 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. 16616
    Prev
    Next
    INDEX
    Explanations

    objects or items that are used as props in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to props and related items used in film or theatrical production

    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
    ihil
    -0.78
    mediated
    -0.74
    ylum
    -0.70
     defer
    -0.69
     retri
    -0.68
     jointly
    -0.68
     complement
    -0.68
    unicip
    -0.66
    wark
    -0.66
    ivo
    -0.65
    POSITIVE LOGITS
     props
    2.03
     pins
    1.82
    olls
    1.76
     switches
    1.59
     screws
    1.53
     magnets
    1.43
     wires
    1.39
     hooks
    1.39
     plugs
    1.37
     pedals
    1.36
    Activations Density 0.057%

    No Known Activations