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. 9-RES-JB
    6. 6840
    Prev
    Next
    INDEX
    Explanations

    references to proper nouns or specific entities

    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
    thood
    -0.83
    ����
    -0.81
    earch
    -0.76
    etsy
    -0.72
    ccoli
    -0.65
    \\\\
    -0.65
    eno
    -0.65
    Ò
    -0.64
    !!!!!!!!
    -0.64
    ounces
    -0.63
    POSITIVE LOGITS
    oret
    1.46
     latter
    1.38
     implication
    1.28
     result
    1.27
     resulting
    1.15
     downside
    1.13
     resultant
    1.12
     remainder
    1.09
     gist
    1.09
     ensuing
    1.09
    Activations Density 0.316%

    No Known Activations