INDEX

Explanations

words related to exploration or investigation

oai_token-act-pair · gpt-3.5-turbo

variations of the letter "o"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 apex

-0.83

 hypot

-0.71

 endif

-0.65

 Horse

-0.65

 Gamb

-0.63

 Accord

-0.63

 Watkins

-0.62

 analogue

-0.61

 adrenaline

-0.61

Rez

-0.60

POSITIVE LOGITS

itative

1.17

itation

1.08

itable

1.08

ilers

1.06

entials

1.05

iled

1.04

ited

1.02

enced

0.98

oved

0.96

verted

0.95

Activations Density 0.056%

words related to exploration or investigation

variations of the letter "o"

No Comments

No Known Activations