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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 14570
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviews or criticism, potentially focusing on specific aspects like quotes, performances, and assessments

    oai_token-act-pair · gpt-3.5-turbo

    references to music and musical performances

    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
     Pwr
    -0.79
    ortium
    -0.74
    rastructure
    -0.69
    teness
    -0.68
    ossibility
    -0.67
    kefeller
    -0.66
    LOD
    -0.65
    thora
    -0.65
    zbollah
    -0.65
    hesda
    -0.65
    POSITIVE LOGITS
     slang
    0.85
     vocabulary
    0.81
     poem
    0.80
     chants
    0.78
     sermon
    0.76
     verse
    0.75
     greeting
    0.74
     verbal
    0.74
     sessions
    0.74
     audible
    0.73
    Activations Density 1.046%

    No Known Activations