© 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. 2-RES-JB
    11. 8288
    Prev
    Next
    INDEX
    Explanations

    the word "Story" capitalized and occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Story"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.81
     stocking
    -0.79
     satell
    -0.78
    utive
    -0.78
    ktop
    -0.77
    ugal
    -0.75
    resent
    -0.73
     depletion
    -0.71
    lav
    -0.70
    plet
    -0.70
    POSITIVE LOGITS
     Story
    1.24
    telling
    1.18
     Stories
    1.05
     Narr
    0.85
    boards
    0.84
     STORY
    0.84
    Story
    0.84
    line
    0.83
    Maker
    0.81
     Transcript
    0.80
    Activations Density 0.011%

    No Known Activations