© 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. 7-RES-JB
    11. 2161
    Prev
    Next
    INDEX
    Explanations

    technical specifications or details

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to specifications and technical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hound
    -1.00
    lift
    -0.88
    etheless
    -0.78
    kus
    -0.78
    winter
    -0.74
    ilee
    -0.69
    hurst
    -0.69
     Sheen
    -0.68
    zees
    -0.67
    kers
    -0.67
    POSITIVE LOGITS
     specifications
    1.24
     Specifications
    1.01
    imens
    0.99
     specs
    0.98
    imen
    0.85
     specification
    0.83
    ifications
    0.81
    eters
    0.78
     specifies
    0.75
    Spec
    0.73
    Activations Density 0.046%

    No Known Activations