INDEX

Explanations

verbs related to being discovered or apprehended

oai_token-act-pair · gpt-3.5-turbo

instances of the word "caught."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ented

-0.64

 delim

-0.63

 sclerosis

-0.63

psey

-0.62

ankind

-0.59

 ceremonies

-0.59

aceutical

-0.58

estate

-0.58

 atmosp

-0.58

 columns

-0.58

POSITIVE LOGITS

 unprepared

0.88

 plagiar

0.79

ãĤ¤ãĥĪ

0.72

 tampering

0.67

netflix

0.67

ãĥ³ãĤ¸

0.67

coni

0.66

bryce

0.64

bys

0.64

 dere

0.64

Activations Density 0.026%

verbs related to being discovered or apprehended

instances of the word "caught."

No Comments

No Known Activations