© 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. 0-RES-JB
    11. 2788
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rocked" and its variants, particularly in contexts related to significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erate
    -0.89
     objection
    -0.80
     calculus
    -0.76
     bluff
    -0.74
     Grimm
    -0.74
     persuasion
    -0.71
     Reserv
    -0.67
     Firearms
    -0.64
     reservation
    -0.64
     Labrador
    -0.63
    POSITIVE LOGITS
     rocked
    2.78
     engulfed
    1.63
     rocking
    1.53
     spanning
    1.42
     engulf
    1.28
    agher
    1.07
     gripped
    1.05
    RIP
    1.05
    adish
    1.03
     envelop
    0.95
    Activations Density 0.063%

    No Known Activations