INDEX

Explanations

phrases beginning with the word "an"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "an"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Borders

-0.81

 Jagu

-0.73

stones

-0.69

 Bris

-0.68

 Blossom

-0.67

 branches

-0.67

 Shake

-0.66

åĮ

-0.66

bottom

-0.65

 Clarkson

-0.65

POSITIVE LOGITS

abolic

0.92

cients

0.85

onymous

0.84

notation

0.79

imes

0.78

agram

0.77

omal

0.76

alysed

0.75

alyses

0.75

omaly

0.74

Activations Density 0.027%

phrases beginning with the word "an"

occurrences of the word "an"

No Comments

No Known Activations