INDEX

Explanations

occurrences of the letter 'A' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enderror

-0.65

quilo

-0.64

Fordítás

-0.60

quela

-0.58

queles

-0.57

 też

-0.54

 springfox

-0.54

 implement

-0.54

cnbc

-0.53

ciclopedia

-0.52

POSITIVE LOGITS

 brief

0.50

 للاسماء

0.50

0.49

few

0.48

 very

0.47

aA

0.47

DllImport

0.45

 little

0.45

 JTable

0.44

arts

0.44

Activations Density 0.230%

occurrences of the letter 'A' in various contexts

No Comments

No Known Activations