© 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. 6-RES-JB
    11. 1505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.89
    çĶ°
    -0.69
    çīĪ
    -0.68
    gdala
    -0.68
    intosh
    -0.67
    ufact
    -0.67
    èĢħ
    -0.66
    Export
    -0.64
    IDA
    -0.62
    INT
    -0.61
    POSITIVE LOGITS
    ties
    0.89
    fire
    0.86
    sk
    0.85
    footed
    0.83
    ty
    0.78
    faced
    0.74
     enough
    0.71
     tack
    0.71
     damn
    0.71
    ples
    0.70
    Activations Density 0.019%

    No Known Activations