© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    phrases related to settings or limitations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to settings and configurations

    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
     die
    -0.82
     parliament
    -0.71
     sustained
    -0.70
     dealers
    -0.69
     slump
    -0.68
     cameo
    -0.66
     dies
    -0.66
     bury
    -0.65
     share
    -0.65
     bye
    -0.65
    POSITIVE LOGITS
    Setting
    2.71
    limits
    1.90
     Setting
    1.68
    Ready
    1.66
    Warning
    1.38
    Bal
    1.38
    Bonus
    1.30
    Creating
    1.23
    Required
    1.22
    WARNING
    1.22
    Activations Density 0.041%

    No Known Activations