© 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. 9-RES-JB
    11. 1752
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative outcomes or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to abrupt and preemptive conclusions or endings

    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
    soType
    -0.82
    models
    -0.74
    rum
    -0.71
    »Ĵ
    -0.69
    redients
    -0.67
    atech
    -0.67
     Boo
    -0.67
    ometers
    -0.67
     Cosponsors
    -0.66
    pects
    -0.65
    POSITIVE LOGITS
     demise
    1.70
     death
    1.65
     destruction
    1.62
     disappearance
    1.56
     annihilation
    1.50
     defeat
    1.46
     removal
    1.45
     deaths
    1.44
     downfall
    1.43
     dissolution
    1.43
    Activations Density 0.901%

    No Known Activations