INDEX

Explanations

phrases related to measuring the size and shape of objects

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and" related to 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

gets

-0.85

rs

-0.74

 Pigs

-0.73

 Kirin

-0.72

aroo

-0.70

hov

-0.69

atican

-0.69

ouls

-0.68

wives

-0.68

KK

-0.68

POSITIVE LOGITS

 likeness

1.15

 temperament

0.98

 uniqueness

0.96

 characteristics

0.94

 stature

0.94

 texture

0.93

 elevation

0.92

 heterogeneity

0.92

 geography

0.91

 composition

0.90

Activations Density 0.358%

phrases related to measuring the size and shape of objects

occurrences of the word "and" related to various contexts

No Comments

No Known Activations