© 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. 2-RES-JB
    11. 12908
    Prev
    Next
    INDEX
    Explanations

    legal or formal language indicating a rule or requirement

    oai_token-act-pair · gpt-3.5-turbo

    the word "shall" indicating future obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advertisement
    -0.72
     Lif
    -0.61
    Newsletter
    -0.61
    killing
    -0.59
    serving
    -0.59
    cule
    -0.59
     Rohing
    -0.59
    packing
    -0.59
    enthal
    -0.59
     Jobs
    -0.58
    POSITIVE LOGITS
    ower
    0.87
     hereafter
    0.86
    owship
    0.86
     gladly
    0.86
     be
    0.83
     endeavour
    0.83
    ghai
    0.82
     surely
    0.81
    ows
    0.80
    otle
    0.79
    Activations Density 0.009%

    No Known Activations