© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    phrases of advice or observations

    oai_token-act-pair · gpt-3.5-turbo

    the word "you" in various contexts and its associated phrases

    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
     è£ıè
    -0.63
    ãĥ³ãĤ¸
    -0.63
    pedia
    -0.63
    ENDED
    -0.61
    temp
    -0.61
    icum
    -0.61
     Verge
    -0.60
    aiden
    -0.60
    Joined
    -0.60
    IME
    -0.59
    POSITIVE LOGITS
    're
    1.41
     gotta
    1.38
     know
    1.19
    've
    1.18
     wanna
    1.13
     guys
    1.11
     realise
    1.08
     realize
    1.02
     cannot
    1.01
     want
    0.98
    Activations Density 0.120%

    No Known Activations