© 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. 22223
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of support or central importance

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to dependence or reliance

    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
     Null
    -0.79
    Cool
    -0.76
    aven
    -0.76
    dos
    -0.75
    fil
    -0.72
     Dos
    -0.70
    chlor
    -0.70
     Cron
    -0.68
     Nu
    -0.64
    ann
    -0.64
    POSITIVE LOGITS
     hinges
    3.53
     hinge
    3.26
     rests
    2.28
     rested
    1.63
     prem
    1.41
     resting
    1.37
     depended
    1.33
     revolves
    1.23
     pedest
    1.18
     springs
    1.16
    Activations Density 0.034%

    No Known Activations