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. 10-RES-JB
    6. 3301
    Prev
    Next
    INDEX
    Explanations

    actions related to interaction with technology or objects

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to actions performed by a subject in various contexts

    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
    vier
    -0.76
    never
    -0.70
    paralle
    -0.70
    ²¾
    -0.70
     millenn
    -0.67
    ameless
    -0.63
     thriving
    -0.59
     pastors
    -0.58
     gladly
    -0.56
     libertarians
    -0.56
    POSITIVE LOGITS
    +.
    0.75
     or
    0.69
     Logged
    0.68
    .",
    0.67
    .","
    0.67
     exceeds
    0.65
     outdoors
    0.64
     touched
    0.63
    .
    0.63
    ().
    0.62
    Activations Density 0.428%

    No Known Activations