© 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. 9-RES-JB
    11. 4949
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing personal beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    discussions about political events and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minds
    -0.17
     dod
    -0.17
     bodies
    -0.17
     defence
    -0.16
     boards
    -0.16
     board
    -0.16
     competition
    -0.16
    ás
    -0.16
     assemb
    -0.16
     civilisation
    -0.15
    POSITIVE LOGITS
    ©¶æ
    0.22
    anse
    0.20
    region
    0.19
    ¼
    0.18
    ĥ
    0.18
    ãĤ´ãĥ³
    0.17
    =~=~
    0.17
    uff
    0.17
    Ĩ
    0.16
    rolet
    0.16
    Activations Density 6.360%

    No Known Activations