© 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. 6-RES-JB
    11. 811
    Prev
    Next
    INDEX
    Explanations

    related to technical terms and specialized vocabulary in various fields

    oai_token-act-pair · gpt-3.5-turbo

    words that describe characteristics or qualities

    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
    ufact
    -0.99
    ĸļ
    -0.98
    urat
    -0.85
    nikov
    -0.84
    soDeliveryDate
    -0.82
    afety
    -0.82
    schild
    -0.81
    orah
    -0.80
    vironment
    -0.78
    lished
    -0.78
    POSITIVE LOGITS
     tendencies
    0.90
     behavior
    0.82
     behaviors
    0.80
     behaviour
    0.80
     technologies
    0.78
     impulses
    0.77
     mechanisms
    0.77
     measures
    0.75
     warfare
    0.75
     interventions
    0.74
    Activations Density 0.167%

    No Known Activations