INDEX

Explanations

instances of repeated or redundant structures in the text

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

$',

-0.71



-0.69

$",

-0.67

IsContent

-0.65

"",

-0.63

ACIN

-0.62

ak

-0.61

﹍﹍﹍

-0.59

ğu

-0.59

len

-0.58

POSITIVE LOGITS

 itſelf

0.98

 myſelf

0.91

 pleaſure

0.86

RenderAtEndOf

0.84

 Jefus

0.82

 leſs

0.81

 poffible

0.80

IsMutable

0.79

 ſche

0.79

 juſ

0.78

Activations Density 0.377%

instances of repeated or redundant structures in the text

No Comments

No Known Activations