© 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. 11028
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing information or insight

    oai_token-act-pair · gpt-3.5-turbo

    the pronouns 'you' and 'us' in various contexts

    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
    uting
    -0.68
     Archdemon
    -0.66
    iffe
    -0.64
    ourgeois
    -0.64
    ute
    -0.63
    ilde
    -0.63
    rating
    -0.61
    annot
    -0.61
    Polit
    -0.60
    nown
    -0.58
    POSITIVE LOGITS
     permission
    1.19
     pause
    1.16
     ample
    1.15
     insight
    1.13
     plenty
    1.08
     access
    1.05
     clues
    1.01
     glimps
    1.00
     insights
    0.99
     nightmares
    0.97
    Activations Density 0.082%

    No Known Activations