© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14327
    Prev
    Next
    INDEX
    Explanations

    names and locations in the format of "First Name, Last Name, City, Age" with a focus on specific numbers representing ages and references to Las Vegas

    oai_token-act-pair · gpt-3.5-turbo

    semicolons in text

    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
     spons
    -0.93
    ħĭ
    -0.85
     attacker
    -0.80
     tremend
    -0.80
     unbeat
    -0.80
     unnecess
    -0.80
     helicop
    -0.77
    icter
    -0.76
     freezer
    -0.75
    senal
    -0.75
    POSITIVE LOGITS
    -)
    1.03
    ;;;;;;;;;;;;
    0.98
    }"
    0.89
     };
    0.89
     thence
    0.80
     }
    0.76
    alias
    0.76
    };
    0.74
     ..........
    0.72
     =====
    0.71
    Activations Density 0.049%

    No Known Activations