INDEX

Explanations

occurrences of the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

CodeAttribute

-0.68

larak

-0.62

RTLE

-0.60

ventus

-0.60

FOOTNOTES

-0.59

",&

-0.58

uny

-0.58

 Humphreys

-0.58

각주

-0.57

thée

-0.57

POSITIVE LOGITS

 dedans

0.77

LookAnd

0.74

 Linz

0.72

 Agrega

0.71

 répon

0.68

 foncé

0.67

 extérieurs

0.67

checkin

0.66

 roulant

0.65

 littéraire

0.64

Activations Density 0.141%

occurrences of the word "in."

No Comments

No Known Activations