© 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. 3744
    Prev
    Next
    INDEX
    Explanations

    phrases related to fulfilling commitments or promises

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fulfilling commitments and responsibilities

    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
     Leilan
    -0.81
    apsed
    -0.74
    ĸļ
    -0.71
    cloth
    -0.70
    iaries
    -0.69
    vine
    -0.66
    ochet
    -0.66
    ischer
    -0.66
    oper
    -0.65
    pora
    -0.65
    POSITIVE LOGITS
     promises
    1.42
     promise
    1.36
     commitments
    1.24
     expectations
    1.22
     obligations
    1.18
     promised
    1.14
     pledges
    1.11
     goals
    1.05
     objectives
    1.04
     aspirations
    1.03
    Activations Density 0.246%

    No Known Activations