INDEX

Explanations

mentions of legal or formal terms and procedures

oai_token-act-pair · gpt-3.5-turbo

discussion of significant experiences and their impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĤ´ãĥ³

-0.64

+.

-0.59

essage

-0.59

etheless

-0.58

avorite

-0.58

anwhile

-0.58

ometimes

-0.57

 respectively

-0.56

eatures

-0.55

 destro

-0.55

POSITIVE LOGITS

,'"

1.12

"—

1.12

,"

1.10

%"

1.08

")

1.03

"]

1.02

"),

0.96

"?

0.95

":

0.95

Activations Density 0.625%

mentions of legal or formal terms and procedures

discussion of significant experiences and their impacts

No Comments

No Known Activations