INDEX

Explanations

instances of repetition or emphasis in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "repeatedly" indicating frequent actions or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reviewer

-0.79

OTA

-0.75

lad

-0.74

soc

-0.72

istan

-0.72

ocene

-0.71

toc

-0.69

rug

-0.67

ofi

-0.67

hemy

-0.67

POSITIVE LOGITS

theless

0.90

 repeated

0.79

 reaff

0.79

 reiter

0.79

è¦ļéĨĴ

0.78

 interrupted

0.77

 contradict

0.77

 incarn

0.76

uously

0.74

entimes

0.73

Activations Density 0.023%

instances of repetition or emphasis in text

instances of the word "repeatedly" indicating frequent actions or behaviors

No Comments

No Known Activations