INDEX

Explanations

references to things being open or opening

oai_token-act-pair · gpt-3.5-turbo

references to "open" spaces or concepts

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

iage

-0.69

illard

-0.65

 Gohan

-0.64

Suc

-0.63

atsu

-0.63

ogun

-0.63

uana

-0.63

Xi

-0.61

IVERS

-0.61

arate

-0.60

POSITIVE LOGITS

 minded

0.79

 scrimmage

0.76

office

0.74

hearted

0.74

ended

0.74

lander

0.74

 doors

0.72

 wounds

0.72

handed

0.72

 spaces

0.71

Activations Density 0.036%

references to things being open or opening

references to "open" spaces or concepts

No Comments

No Known Activations