© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to physical actions or body parts

    oai_token-act-pair · gpt-3.5-turbo

    actions that initiate or commence events

    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
     entirety
    -0.70
    inals
    -0.69
    ighth
    -0.68
    odes
    -0.65
    é¾įå
    -0.65
     ancestors
    -0.64
    arton
    -0.64
    obi
    -0.64
    rero
    -0.63
    enegger
    -0.63
    POSITIVE LOGITS
     anew
    1.07
     behaving
    0.87
     raining
    0.83
     screaming
    0.82
     leaking
    0.82
     fuss
    0.81
     banging
    0.81
     unravel
    0.81
     noticing
    0.79
     pouring
    0.79
    Activations Density 0.069%

    No Known Activations