INDEX

Explanations

instances of the word "see" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

the phrase "see" 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

prime

-0.74

ÃŃa

-0.67

 whistle

-0.67

trap

-0.61

cult

-0.61

 posing

-0.59

tip

-0.59

conn

-0.59

EStreamFrame

-0.59

 understatement

-0.59

POSITIVE LOGITS

dust

0.83

enance

0.80

awed

0.73

 daylight

0.73

lights

0.73

 firsthand

0.71

inelli

0.71

eye

0.70

 visions

0.67

oleon

0.66

Activations Density 0.077%

instances of the word "see" followed by a numerical value

the phrase "see" in various contexts

No Comments

No Known Activations