© 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. 11-RES-JB
    11. 21447
    Prev
    Next
    INDEX
    Explanations

    phrases related to shifts, changes, new ways of thinking, or transformations in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with paradigms and narratives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sight
    -0.76
    OTOS
    -0.72
    ishable
    -0.70
    enegger
    -0.69
    llah
    -0.68
    enary
    -0.67
    adows
    -0.67
    ighters
    -0.66
    Numbers
    -0.65
    akov
    -0.65
    POSITIVE LOGITS
     shift
    1.15
     underpin
    1.07
     Shift
    1.02
     paradigm
    0.98
     perme
    0.98
     perv
    0.92
     clash
    0.91
     whereby
    0.89
     dictated
    0.88
     hegemony
    0.87
    Activations Density 0.239%

    No Known Activations