© 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. 8-RES-JB
    11. 6184
    Prev
    Next
    INDEX
    Explanations

    words related to energy and dietary habits

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to obtaining or acquiring something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grizz
    -0.71
    borough
    -0.71
     Ange
    -0.70
     Mou
    -0.67
     Tie
    -0.65
     Spears
    -0.65
     Goose
    -0.64
     Angola
    -0.64
     Chim
    -0.63
     Sett
    -0.63
    POSITIVE LOGITS
    istical
    1.32
    ical
    1.14
    ically
    1.12
    istic
    1.05
    rical
    1.04
    istically
    1.02
    ics
    1.00
    ect
    0.98
    arist
    0.95
    ologically
    0.95
    Activations Density 0.117%

    No Known Activations