INDEX

Explanations

dates or durations of time, with a focus on "nearly"

oai_token-act-pair · gpt-3.5-turbo

the word "nearly" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

agate

-0.95

Reviewer

-0.75

oris

-0.75

oran

-0.70

ysis

-0.69

DH

-0.68

 locality

-0.66

 messenger

-0.66

":[

-0.66

iless

-0.66

POSITIVE LOGITS

 identical

0.79

stress

0.72

 tripled

0.68

 ident

0.66

arser

0.65

ceed

0.65

iannopoulos

0.65

 finished

0.64

PsyNetMessage

0.63

 limitless

0.63

Activations Density 0.035%

dates or durations of time, with a focus on "nearly"

the word "nearly" in various contexts

No Comments

No Known Activations