INDEX

Explanations

nouns related to collections

oai_token-act-pair · gpt-3.5-turbo

references to collections of items or themes

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

pher

-0.83

yl

-0.68

forth

-0.66

 unden

-0.65

expected

-0.61

acl

-0.60

mic

-0.58

runner

-0.57

abad

-0.57

generic

-0.56

POSITIVE LOGITS

collection

0.98

 collection

0.96

 collections

0.90

 Collection

0.90

ĸļ

0.87

 Collections

0.84

uably

0.81

naire

0.80

icles

0.79

ngth

0.76

Activations Density 0.024%

nouns related to collections

references to collections of items or themes

No Comments

No Known Activations