INDEX

Explanations

conversational cues, questions, and claims that reflect uncertainty or seek clarification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Мексичка

-0.80

 snippetHide

-0.79

UserScript

-0.77

DoubleQuotes

-0.74

TagMode

-0.72

Rüyada

-0.70

:");

-0.70

-0.69

InputTagHelper

-0.69

!")

-0.68

POSITIVE LOGITS

↵↵

0.68

<eos>

0.67

↵

0.64

 Good

0.61

0.55

क

0.52

 Looks

0.52

Good

0.52

Super

0.51

edit

0.50

Activations Density 0.271%

conversational cues, questions, and claims that reflect uncertainty or seek clarification

No Comments

No Known Activations