INDEX

Explanations

statements expressing opinion or providing commentary

oai_token-act-pair · gpt-3.5-turbo

assertions or statements being made about various topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hebdo

-0.67

aq

-0.67

 dissolve

-0.65

©¶æ¥µ

-0.64

 strand

-0.58

hid

-0.57

 disappear

-0.56

Tu

-0.56

Daily

-0.56

 dams

-0.55

POSITIVE LOGITS

é¾įåĸļå£«

0.77

udos

0.72

VERTISEMENT

0.71

RIS

0.67

 THANK

0.67

vantage

0.66

haps

0.66

 Rouge

0.66

ENE

0.65

reci

0.64

Activations Density 0.296%

statements expressing opinion or providing commentary

assertions or statements being made about various topics

No Comments

No Known Activations