© 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. 1-RES-JB
    11. 24121
    Prev
    Next
    INDEX
    Explanations

    phrases related to rejection or avoidance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shun" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Grant
    -0.68
    -----------
    -0.64
    onian
    -0.63
    ACTED
    -0.63
    Elect
    -0.62
    assies
    -0.62
    arcity
    -0.62
     Oper
    -0.62
    odore
    -0.61
    hesive
    -0.60
    POSITIVE LOGITS
     shun
    1.34
    ned
    1.17
    owship
    0.87
    rily
    0.84
    ting
    0.84
    hovah
    0.82
    awei
    0.81
    ivas
    0.78
     Canaver
    0.77
    pling
    0.75
    Activations Density 0.009%

    No Known Activations