© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    phrases related to a particular person or brand name that includes the word "riddle"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "riddle" and its variations

    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
    BuyableInstoreAndOnline
    -0.71
    uz
    -0.70
    tan
    -0.69
    icka
    -0.67
     princ
    -0.65
     mil
    -0.63
    ult
    -0.63
    emp
    -0.63
    casts
    -0.62
    catentry
    -0.62
    POSITIVE LOGITS
    iddles
    1.20
    iddled
    1.02
    iddle
    1.00
    iddling
    0.85
    glers
    0.85
    eer
    0.82
    eering
    0.81
    hyde
    0.78
    iddler
    0.76
     tatt
    0.75
    Activations Density 0.010%

    No Known Activations