© 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. 7-RES-JB
    11. 16802
    Prev
    Next
    INDEX
    Explanations

    mentions of senior positions in organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and positions related to senior roles in an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.64
    erella
    -0.62
     Janeiro
    -0.61
     Remastered
    -0.60
     damned
    -0.59
    ãĥ¼ãĥĨ
    -0.59
    NetMessage
    -0.59
     fung
    -0.58
     extremes
    -0.58
    orius
    -0.58
    POSITIVE LOGITS
    imester
    0.74
    urdue
    0.74
    endment
    0.68
     Ake
    0.63
    utenant
    0.60
    jun
    0.59
    arsity
    0.58
    selage
    0.58
     Sly
    0.58
    ISA
    0.57
    Activations Density 0.163%

    No Known Activations