INDEX

Explanations

words related to proper nouns

oai_token-act-pair · gpt-3.5-turbo

words related to forms or structures

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

prints

-0.73

 Decker

-0.68

 Rico

-0.66

lder

-0.65

 Maya

-0.64

Fas

-0.64

Fey

-0.63

print

-0.62

 Absent

-0.61

cho

-0.61

POSITIVE LOGITS

orph

1.04

ont

0.94

etheus

0.89

orm

0.88

ingo

0.87

ammu

0.86

ontent

0.85

inational

0.85

orthy

0.85

yss

0.85

Activations Density 0.016%

words related to proper nouns

words related to forms or structures

No Comments

No Known Activations