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. 9-RES-JB
    6. 11820
    Prev
    Next
    INDEX
    Explanations

    phrases involving comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "say"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è£ħ
    -0.65
    DAQ
    -0.58
     Balanced
    -0.58
     Flavoring
    -0.57
    Newsletter
    -0.57
    fox
    -0.56
    PF
    -0.56
    èĪ
    -0.56
    viks
    -0.55
    è£
    -0.55
    POSITIVE LOGITS
     uh
    1.39
     um
    1.26
    say
    1.02
     ah
    1.01
    wait
    1.01
     oh
    1.00
     say
    0.99
     yeah
    0.92
     gasp
    0.87
     yes
    0.82
    Activations Density 0.110%

    No Known Activations