INDEX

Explanations

words related to clothing

oai_token-act-pair · gpt-3.5-turbo

references to "top" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 warr

-0.77

Ã±a

-0.65

riages

-0.64

 consent

-0.63

ãĥ£

-0.61

 Arri

-0.61

 discern

-0.60

arbon

-0.60

 Hurricanes

-0.59

itizen

-0.59

POSITIVE LOGITS

top

1.19

tops

1.03

most

0.95

TOP

0.95

bottom

0.93

ronics

0.90

mast

0.88

ICS

0.88

ography

0.88

ology

0.86

Activations Density 0.010%

words related to clothing

references to "top" in various contexts

No Comments

No Known Activations