© 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. 9135
    Prev
    Next
    INDEX
    Explanations

    phrases related to job positions and changes within a company

    oai_token-act-pair · gpt-3.5-turbo
    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
    bath
    -0.60
     Examples
    -0.60
     descendants
    -0.58
    lex
    -0.58
    orial
    -0.58
    CONCLUS
    -0.58
    asia
    -0.58
    soDeliveryDate
    -0.57
    ritch
    -0.56
    sted
    -0.56
    POSITIVE LOGITS
     previously
    1.68
     formerly
    1.31
     originally
    1.29
     hitherto
    1.28
     hoped
    1.22
     initially
    1.09
     previous
    1.09
     anticipated
    1.05
     planned
    1.04
     feared
    1.03
    Activations Density 0.513%

    No Known Activations