INDEX

Explanations

numbers in a specific range

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a quantity or number of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bet

-0.63

 fert

-0.61

uala

-0.59

 mixture

-0.59

Effects

-0.58

 blend

-0.58

hunt

-0.58

 sensit

-0.57

 kale

-0.55

agher

-0.55

POSITIVE LOGITS

uits

0.82

ources

0.74

 dozen

0.70

ĳå£«

0.68

icial

0.64

 presidents

0.63

 course

0.62

 majors

0.61

 consecutive

0.61

neys

0.61

Activations Density 0.087%

numbers in a specific range

phrases indicating a quantity or number of entities

No Comments

No Known Activations