INDEX

Explanations

comparisons using the word "than"

oai_token-act-pair · gpt-3.5-turbo

comparative phrases emphasizing a preference or contrast

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

uto

-0.72

ero

-0.65

ongo

-0.64

ISSION

-0.64

imity

-0.59

optional

-0.59

 Juda

-0.59

 exemptions

-0.59

onomy

-0.59

lied

-0.58

POSITIVE LOGITS

 usual

0.82

atos

0.75

 anything

0.73

acles

0.73

adelphia

0.71

 ever

0.70

atever

0.65

 bother

0.65

acle

0.65

 anybody

0.64

Activations Density 0.055%

comparisons using the word "than"

comparative phrases emphasizing a preference or contrast

No Comments

No Known Activations