© 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. 6156
    Prev
    Next
    INDEX
    Explanations

    verbs that are in past participle form

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and its usage in various contexts

    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
    soDeliveryDate
    -0.68
    tions
    -0.66
     Telegram
    -0.63
     trusting
    -0.62
     Giovanni
    -0.59
    letters
    -0.59
     Lemon
    -0.58
    Choice
    -0.58
     Alley
    -0.58
    standing
    -0.57
    POSITIVE LOGITS
     enhance
    1.25
     promote
    1.25
     justify
    1.22
     motivate
    1.18
     maximize
    1.18
     create
    1.16
     protect
    1.14
     preserve
    1.14
     refine
    1.13
     facilitate
    1.13
    Activations Density 0.115%

    No Known Activations