INDEX

Explanations

adjectives describing the degree or intensity of something

oai_token-act-pair · gpt-3.5-turbo

adjectives that express intensity or degree

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

dress

-0.76

ictions

-0.75

 IMAGES

-0.74

ividual

-0.74

ULE

-0.73

 Videos

-0.73

ggles

-0.72

 executes

-0.70

dos

-0.70

doms

-0.70

POSITIVE LOGITS

 unlikely

0.90

 reliant

0.90

 evident

0.89

 noticeable

0.88

 difficult

0.87

 enough

0.86

 susceptible

0.84

 accurate

0.83

 likely

0.83

 dependent

0.82

Activations Density 0.287%

adjectives describing the degree or intensity of something

adjectives that express intensity or degree

No Comments

No Known Activations