© 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
    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. 4748
    Prev
    Next
    INDEX
    Explanations

    titles or descriptions related to the positions of "senior fellow" at various organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and affiliations of individuals, likely related to their professional roles

    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
    MSN
    -0.74
     Schedule
    -0.68
     negro
    -0.67
    Results
    -0.66
     Customers
    -0.65
     growers
    -0.64
    mt
    -0.63
     performers
    -0.62
     stret
    -0.62
     OFFIC
    -0.62
    POSITIVE LOGITS
     Brookings
    0.98
     nonpartisan
    0.85
    cipled
    0.85
    negie
    0.82
     RAND
    0.81
    odox
    0.80
     libertarian
    0.79
    remlin
    0.79
     consultancy
    0.79
     cybersecurity
    0.78
    Activations Density 0.271%

    No Known Activations