INDEX

Explanations

adjectives and nouns indicating a negative assessment or criticism

oai_token-act-pair · gpt-3.5-turbo

terms related to complexity and complications

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

hyde

-0.84

EStream

-0.82

plane

-0.72

 slash

-0.71

terday

-0.67

hoe

-0.67

laus

-0.67

eele

-0.66

 garlic

-0.64

xon

-0.64

POSITIVE LOGITS

acent

1.25

icating

1.12

icates

1.05

icit

1.04

icated

1.03

ainer

0.99

aint

0.97

ications

0.96

aints

0.92

iance

0.91

Activations Density 0.015%

adjectives and nouns indicating a negative assessment or criticism

terms related to complexity and complications

No Comments

No Known Activations