INDEX

Explanations

instances of items that are considered essential or characteristic within a specific context

oai_token-act-pair · gpt-3.5-turbo

phrases related to fundamental or essential components of various contexts

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

odore

-0.91

aline

-0.83

oÄŁ

-0.82

jri

-0.79

ivil

-0.78

sterdam

-0.76

acs

-0.75

apist

-0.75

Parents

-0.75

vernment

-0.72

POSITIVE LOGITS

 pillars

0.82

tenance

0.82

 pillar

0.77

ãĥŁ

0.77

 Breaker

0.74

warts

0.73

stones

0.71

 staples

0.69

 staple

0.69

stay

0.68

Activations Density 0.048%

instances of items that are considered essential or characteristic within a specific context

phrases related to fundamental or essential components of various contexts

No Comments

No Known Activations