Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22320
    Prev
    Next
    INDEX
    Explanations

    verbs with the infinitive form "to" followed by another word, such as "to be", "to go", etc

    oai_token-act-pair · gpt-3.5-turbo

    expressions of decisions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Explan
    -0.70
    til
    -0.65
     Provided
    -0.62
    generated
    -0.59
     looms
    -0.59
    grain
    -0.59
    (-
    -0.58
     Detected
    -0.58
    valued
    -0.58
    anned
    -0.58
    POSITIVE LOGITS
     pursue
    1.27
     postpone
    1.20
     dedicate
    1.19
     donate
    1.17
     settle
    1.16
     ignore
    1.12
     explore
    1.11
     revisit
    1.11
     give
    1.11
     investigate
    1.07
    Activations Density 0.086%

    No Known Activations