© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 22791
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to technical specifications or details

    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
    hound
    -0.80
    lift
    -0.78
    luaj
    -0.76
    friend
    -0.72
    ience
    -0.72
    station
    -0.72
    arma
    -0.72
    kus
    -0.72
    luck
    -0.71
    etheless
    -0.70
    POSITIVE LOGITS
     specifications
    1.10
    imens
    0.84
     specs
    0.82
     dictates
    0.79
     Specifications
    0.79
     specification
    0.79
     dictate
    0.77
     sheet
    0.76
     promulg
    0.75
     specifies
    0.75
    Activations Density 0.093%

    No Known Activations