© 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. 17777
    Prev
    Next
    INDEX
    Explanations

    phrases related to disadvantages or being at a disadvantage in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disadvantage and its implications

    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
     applic
    -0.70
    addle
    -0.67
     manic
    -0.65
     delivery
    -0.64
    sis
    -0.61
    ramid
    -0.58
     matt
    -0.58
     deposit
    -0.58
     nails
    -0.57
     hooks
    -0.57
    POSITIVE LOGITS
     disadvant
    1.01
     disadvantage
    0.86
    ous
    0.80
     inferior
    0.76
    lessly
    0.75
    itism
    0.75
    ccess
    0.74
     facing
    0.73
    pora
    0.72
     disadvantages
    0.72
    Activations Density 0.020%

    No Known Activations