© 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. 20079
    Prev
    Next
    INDEX
    Explanations

    phrases related to traveling by plane

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable situations

    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
     disappoint
    -0.64
     plac
    -0.63
     AFP
    -0.63
     plate
    -0.62
     pleased
    -0.61
    ascade
    -0.60
    Adam
    -0.60
    Tex
    -0.60
    png
    -0.60
    hap
    -0.59
    POSITIVE LOGITS
    rums
    0.80
     Psychiatric
    0.75
    etic
    0.70
     Clockwork
    0.70
     Ans
    0.69
    ei
    0.67
    minecraft
    0.67
    ÃŃn
    0.66
    thur
    0.65
     Sorce
    0.63
    Activations Density 0.000%

    No Known Activations