© 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. 7-RES-JB
    11. 15667
    Prev
    Next
    INDEX
    Explanations

    the word "somehow," often present before surprising or unexpected events or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "somehow" in various contexts

    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
    rike
    -0.69
    yer
    -0.65
    emies
    -0.64
    yrs
    -0.64
    oft
    -0.64
     Parenthood
    -0.64
    pu
    -0.63
    imens
    -0.63
    anon
    -0.62
    rament
    -0.62
    POSITIVE LOGITS
     somew
    1.18
     magically
    1.01
     managed
    0.91
     somehow
    0.88
     else
    0.83
    Else
    0.81
     mirac
    0.81
     manage
    0.79
     unaccount
    0.75
     resembling
    0.75
    Activations Density 0.031%

    No Known Activations