INDEX

Explanations

high-impact words or phrases that evoke strong emotions or reactions

oai_token-act-pair · gpt-3.5-turbo

capital letters or proper nouns

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

EStream

-0.75

 Hobbit

-0.73

 Wast

-0.69

 Oath

-0.69

 pony

-0.68

 Alchemist

-0.68

foundland

-0.66

LOD

-0.62

Ħ¢

-0.61

hyde

-0.60

POSITIVE LOGITS

cially

1.10

itting

1.07

rarily

1.06

ually

1.06

itionally

1.04

ifully

1.03

cknowled

1.02

ately

1.00

aring

0.99

quartered

0.99

Activations Density 0.236%

high-impact words or phrases that evoke strong emotions or reactions

capital letters or proper nouns

No Comments

No Known Activations