© 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. 8-RES-JB
    11. 875
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulations or legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thous
    -0.61
     suspic
    -0.59
    enegger
    -0.56
    etheless
    -0.55
     millenn
    -0.54
    chuk
    -0.53
    ĵĺ
    -0.52
     Palestin
    -0.50
     strained
    -0.50
     WATCHED
    -0.50
    POSITIVE LOGITS
    oft
    0.74
     clause
    0.71
    ively
    0.66
    matter
    0.64
     mode
    0.64
    aroo
    0.63
    ivist
    0.61
    arium
    0.61
     clauses
    0.60
    less
    0.59
    Activations Density 1.033%

    No Known Activations