INDEX

Explanations

phrases related to toughness or strength

oai_token-act-pair · gpt-3.5-turbo

variations of the word "ough" and its related morphological forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Copenhagen

-0.69

 Lisbon

-0.67

piece

-0.65

 Lutheran

-0.64

 Wand

-0.61

 Triumph

-0.61

 Borough

-0.61

 Carlson

-0.60

crew

-0.60

 Emin

-0.60

POSITIVE LOGITS

oug

1.29

hest

1.09

avored

0.96

heed

0.88

omen

0.87

lean

0.84

itives

0.83

cipl

0.81

ener

0.81

isoft

0.80

Activations Density 0.028%

phrases related to toughness or strength

variations of the word "ough" and its related morphological forms

No Comments

No Known Activations