© 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. 10-RES-JB
    11. 23448
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating the intensity of a feeling or situation

    oai_token-act-pair · gpt-3.5-turbo

    emphatic adjectives that indicate strong feelings or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idth
    -0.74
    ourses
    -0.71
    iphate
    -0.68
    rities
    -0.67
    rients
    -0.66
    ership
    -0.66
    essor
    -0.66
    enaries
    -0.65
    rals
    -0.65
    DragonMagazine
    -0.64
    POSITIVE LOGITS
     difficult
    1.33
     ironic
    1.33
     frustrating
    1.24
     easy
    1.18
     tempting
    1.18
     unlikely
    1.17
     obvious
    1.16
     impossible
    1.14
     unfair
    1.14
     imperative
    1.14
    Activations Density 0.177%

    No Known Activations