© 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. 9-RES-JB
    11. 17930
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals, intentions, and purposes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to intentions and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    lex
    -0.70
    bats
    -0.69
    cloth
    -0.67
    batch
    -0.65
    uberty
    -0.65
    Berry
    -0.61
    cephal
    -0.60
     harshly
    -0.59
     aval
    -0.59
    electric
    -0.59
    POSITIVE LOGITS
     goal
    2.09
     purpose
    1.89
     objectives
    1.85
     aim
    1.83
     goals
    1.79
     objective
    1.76
     aims
    1.60
     Purpose
    1.57
    goal
    1.57
     intention
    1.48
    Activations Density 1.161%

    No Known Activations