© 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. 11-RES-JB
    11. 22474
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching, seeking, or finding something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to searching for options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imony
    -0.83
    otypes
    -0.76
    idium
    -0.75
    naires
    -0.75
    images
    -0.72
    oids
    -0.72
    redits
    -0.71
    IPS
    -0.70
    events
    -0.69
    ivities
    -0.68
    POSITIVE LOGITS
     way
    1.47
     solution
    1.26
     workaround
    1.24
     scapego
    1.23
     loophole
    1.23
     suitable
    1.21
     cure
    1.17
     replacement
    1.17
     successor
    1.08
     remedy
    1.05
    Activations Density 0.139%

    No Known Activations