© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    phrases that are formatted in a specific way (e.g., starting with bullet points followed by sentences in italics)

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific numerical values or measurements related to evaluations or observations

    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
     estranged
    -0.85
     ageing
    -0.70
     endeav
    -0.68
     somew
    -0.65
     tink
    -0.62
     canv
    -0.62
     slowing
    -0.62
     hypers
    -0.62
     unaff
    -0.62
     pir
    -0.61
    POSITIVE LOGITS
    Notable
    1.05
    However
    1.03
    Example
    1.00
    Examples
    0.97
    Furthermore
    0.96
    Additionally
    0.95
    Also
    0.95
    Specifically
    0.92
    ONSORED
    0.89
    Its
    0.88
    Activations Density 0.421%

    No Known Activations