INDEX

Explanations

specific instances or occurrences of something within a larger context

oai_token-act-pair · gpt-3.5-turbo

the word "the" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rehend

-0.76

 namely

-0.75

 thereby

-0.74

thood

-0.74

ategory

-0.72

ufact

-0.71

ucl

-0.71

 ensured

-0.70

hound

-0.68

beit

-0.68

POSITIVE LOGITS

 same

1.23

 beginnings

1.21

 aftermath

1.14

 difference

1.13

 devastation

1.12

 entirety

1.08

 slightest

1.07

 brunt

1.02

 results

1.00

 similarities

0.97

Activations Density 0.198%

specific instances or occurrences of something within a larger context

the word "the" and its variations in context

No Comments

No Known Activations