INDEX

Explanations

phrases related to checking for specific conditions or items

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the act of checking or searching for something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.83

orld

-0.80

alore

-0.71

soever

-0.68

beit

-0.67

ername

-0.65

nor

-0.65

Ã£

-0.64

operated

-0.64

adra

-0.64

POSITIVE LOGITS

 clues

0.98

gery

0.84

geries

0.82

WARD

0.78

 vulnerabilities

0.77

gotten

0.76

 signs

0.76

 conting

0.75

 inclusion

0.74

 instance

0.73

Activations Density 0.139%

phrases related to checking for specific conditions or items

phrases that indicate the act of checking or searching for something

No Comments

No Known Activations