INDEX

Explanations

words related to conducting trials or experiments

oai_token-act-pair · gpt-3.5-turbo

the repeated instances of the word "test" and its variations, indicating a focus on evaluation or experimentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

taboola

-0.72

brance

-0.71

lance

-0.69

nown

-0.68

\-

-0.66

vation

-0.65

ometown

-0.65

nick

-0.63

apo

-0.63

ffe

-0.63

POSITIVE LOGITS

 hypotheses

0.98

osterone

0.88

ifies

0.81

orously

0.80

 whether

0.80

 hypothesis

0.70

ify

0.69

imon

0.69

 feasibility

0.68

onom

0.68

Activations Density 0.078%

words related to conducting trials or experiments

the repeated instances of the word "test" and its variations, indicating a focus on evaluation or experimentation

No Comments

No Known Activations