INDEX

Explanations

references to possessive form with an apostrophe followed by an 's' and a singular noun

oai_token-act-pair · gpt-3.5-turbo

the letter 's' in various contexts

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

Compare

-0.72

 Lauder

-0.71

 Compare

-0.71

lude

-0.68

 Berger

-0.64

leans

-0.62

bench

-0.61

roup

-0.61

lehem

-0.61

inyl

-0.61

POSITIVE LOGITS

own

1.22

selves

1.09

ELF

1.09

 inability

0.99

 plight

0.99

 grasp

0.96

 reputation

0.96

 shortcomings

0.95

 predicament

0.95

self

0.94

Activations Density 0.227%

references to possessive form with an apostrophe followed by an 's' and a singular noun

the letter 's' in various contexts

No Comments

No Known Activations