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. 7-RES-JB
    6. 2073
    Prev
    Next
    INDEX
    Explanations

    unintelligible or garbled characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of key terms related to responsibility and obligations

    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
     Haku
    -0.79
     Sob
    -0.78
     Yad
    -0.77
     Raf
    -0.73
     Fritz
    -0.72
     Clara
    -0.71
    ĸļ
    -0.70
     Nish
    -0.70
     Rik
    -0.70
     Mub
    -0.69
    POSITIVE LOGITS
    ó
    1.24
    Loading
    1.10
    together
    1.05
    Commission
    1.05
    Ident
    1.05
    Reply
    1.04
    MAS
    1.02
    Contribut
    1.02
    acqu
    1.01
    French
    1.01
    Activations Density 0.115%

    No Known Activations