INDEX

Explanations

exceptions or conditions that invalidate a general statement

oai_token-act-pair · gpt-3.5-turbo

the word "except" and its variations used in context

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

ushed

-0.63

mob

-0.63

gged

-0.63

ossom

-0.62

acia

-0.62

ushing

-0.62

Äĩ

-0.61

uld

-0.60

avan

-0.60

yrs

-0.59

POSITIVE LOGITS

ional

1.06

 insofar

0.82

heses

0.75

livious

0.67

inarily

0.64

arus

0.63

 except

0.62

Â¯

0.61

icularly

0.61

withstanding

0.61

Activations Density 0.023%

exceptions or conditions that invalidate a general statement

the word "except" and its variations used in context

No Comments

No Known Activations