Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 3309
    Prev
    Next
    INDEX
    Explanations

    verbs relating to accomplishing or reaching a goal

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of achieving goals or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cloth
    -0.68
    otta
    -0.67
    seed
    -0.65
    RNA
    -0.63
    ©¶æ
    -0.63
    sbm
    -0.62
    osate
    -0.61
    letter
    -0.61
     scanned
    -0.60
     Frie
    -0.60
    POSITIVE LOGITS
     attainment
    0.92
     mastery
    0.89
    ments
    0.84
     greatness
    0.83
     fruition
    0.82
    iage
    0.82
     achievement
    0.81
     accomplish
    0.81
    chieve
    0.80
     parity
    0.80
    Activations Density 0.039%

    No Known Activations