Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20299
    Prev
    Next
    INDEX
    Explanations

    pronouns 'he' and 'she' along with accompanying verbs and contextual information

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endif
    -0.81
     expiration
    -0.77
     antioxid
    -0.74
     expire
    -0.67
     trem
    -0.65
     ripple
    -0.62
    reach
    -0.61
     endif
    -0.60
     rejoice
    -0.59
    stay
    -0.58
    POSITIVE LOGITS
    aped
    1.20
    uristic
    1.07
    'd
    1.07
     deems
    1.07
     remembers
    1.04
     alleges
    1.02
     believes
    1.01
    aps
    1.01
     describes
    1.00
     considers
    0.99
    Activations Density 0.124%

    No Known Activations