INDEX

Explanations

phrases indicating accomplishment or achievement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "have" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

osa

-0.67

 Sparrow

-0.62

ologically

-0.59

 Crus

-0.59

Subject

-0.58

 Tanz

-0.57

 Moons

-0.57

osion

-0.57

winner

-0.56

 Shots

-0.56

POSITIVE LOGITS

 been

1.26

been

1.12

theless

1.06

 Been

1.04

gotten

0.97

 gotten

0.91

 gone

0.87

ighed

0.85

gged

0.84

 undergone

0.84

Activations Density 0.036%

phrases indicating accomplishment or achievement

instances of the word "have" in various contexts

No Comments

No Known Activations