INDEX

Explanations

occurrences of the word "first" and its variants 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

%)$

-0.87

ItemBackground

-0.86

protoimpl

-0.83

enumii

-0.82

parsedMessage

-0.78

PyExc

-0.77

"}")

-0.76

 itſelf

-0.76

welli

-0.73

hésite

-0.73

POSITIVE LOGITS

 ever

0.95

 First

0.75

few

0.73

 responders

0.70

FIRST

0.70

Ever

0.69

 Ever

0.68

 impressions

0.68

 FIRST

0.68

First

0.66

Activations Density 0.168%

occurrences of the word "first" and its variants in various contexts

No Comments

No Known Activations