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. 8-RES-JB
    6. 5961
    Prev
    Next
    INDEX
    Explanations

    personal identity and classification statements

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns or affirmations of identity, particularly related to being a woman and racial identity

    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
     snacks
    -0.77
     fortun
    -0.71
     publicity
    -0.70
     seiz
    -0.69
    çīĪ
    -0.67
     telesc
    -0.63
     ACS
    -0.63
     Circus
    -0.63
     srfAttach
    -0.63
    ãĥ¼ãĥĨ
    -0.63
    POSITIVE LOGITS
    Ļ
    1.24
    ¤
    1.21
    ª
    1.15
    ¬
    1.13
    £
    1.08
    Ĵ
    1.07
    ħ
    1.06
    ĸ
    1.05
    Ķ
    1.05
    ¼
    1.02
    Activations Density 0.200%

    No Known Activations