INDEX

Explanations

phrases related to intense situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sense" in various contexts

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

warts

-0.81

Accessory

-0.75

skill

-0.73

leaders

-0.71

swick

-0.70

abad

-0.70

aston

-0.70

oths

-0.67

talking

-0.67

utor

-0.67

POSITIVE LOGITS

mble

1.91

ly

0.96

ense

0.81

entimes

0.78

iture

0.73

ENSE

0.69

cre

0.69

lessly

0.67

ãĥĨãĤ£

0.66

LY

0.65

Activations Density 0.025%

phrases related to intense situations

instances of the word "sense" in various contexts

No Comments

No Known Activations