© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    phrases related to services or information provided for the ease and benefit of users

    oai_token-act-pair · gpt-3.5-turbo

    references to convenience and related concepts

    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
    ynt
    -0.72
    hips
    -0.69
    orn
    -0.67
    REE
    -0.67
    gans
    -0.66
    FLAG
    -0.65
    orns
    -0.65
    volent
    -0.62
    AMS
    -0.62
    Edited
    -0.62
    POSITIVE LOGITS
     convenience
    1.09
     gratification
    0.89
    venient
    0.86
    iences
    0.79
     familiarity
    0.77
     booths
    0.75
     ratios
    0.74
    oire
    0.73
    iliar
    0.73
     conven
    0.72
    Activations Density 0.008%

    No Known Activations