© 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. 3-RES-JB
    11. 15158
    Prev
    Next
    INDEX
    Explanations

    words or parts of words ending in 'ap'

    oai_token-act-pair · gpt-3.5-turbo

    the word 'ap' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.76
     phyl
    -0.72
     Monstrous
    -0.70
     cigars
    -0.67
     Masquerade
    -0.66
    knit
    -0.65
     cig
    -0.63
    milo
    -0.61
    tty
    -0.59
     kosher
    -0.59
    POSITIVE LOGITS
    oleon
    1.21
    olitan
    1.21
    apa
    1.12
    artment
    1.11
    ocalypse
    1.11
    ocalyptic
    1.11
    ropri
    1.10
    ower
    1.09
    onent
    1.09
    alm
    1.07
    Activations Density 0.018%

    No Known Activations