© 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. 21363
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by phrases indicating a personal association or desire

    oai_token-act-pair · gpt-3.5-turbo

    the speaker's expressions of personal thoughts and desires

    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
     ubiqu
    -0.65
     diam
    -0.63
    ugen
    -0.63
     Travels
    -0.60
    ahime
    -0.59
    entric
    -0.58
     invis
    -0.57
     unequ
    -0.56
    ruary
    -0.56
    ith
    -0.55
    POSITIVE LOGITS
     ever
    1.04
     cared
    0.89
     needed
    0.85
     wanna
    0.85
     gotta
    0.83
     need
    0.82
     EVER
    0.81
     ask
    0.80
     know
    0.78
     want
    0.78
    Activations Density 0.065%

    No Known Activations