© 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. 10-RES-JB
    6. 21690
    Prev
    Next
    INDEX
    Explanations

    phrases related to political conflict and militant groups

    oai_token-act-pair · gpt-3.5-turbo

    references to possessive pronouns and their corresponding objects or subjects, indicating ownership or relation to a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ****
    -0.81
    -------
    -0.76
    Enable
    -0.74
    Initialized
    -0.73
    anza
    -0.72
    NetMessage
    -0.71
    gio
    -0.70
    imal
    -0.70
    ucket
    -0.69
    olt
    -0.69
    POSITIVE LOGITS
     attendant
    1.59
     allies
    1.41
     associated
    1.37
     accompanying
    1.33
     il
    1.30
     affiliates
    1.25
     successors
    1.23
     equivalents
    1.21
     derivatives
    1.15
     related
    1.15
    Activations Density 0.104%

    No Known Activations