INDEX

Explanations

proper nouns related to specific locations or events

oai_token-act-pair · gpt-3.5-turbo

references to notes or documentation

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

hips

-0.85

ipal

-0.83

antha

-0.78

owship

-0.76

Ļ½

-0.75

quished

-0.73

ahoo

-0.70

BIP

-0.69

 ILCS

-0.68

aciously

-0.67

POSITIVE LOGITS

chnology

1.08

chn

1.04

OPLE

0.99

zzi

0.90

legates

0.90

lete

0.85

ptic

0.80

legate

0.75

peat

0.74

ktop

0.74

Activations Density 0.055%

proper nouns related to specific locations or events

references to notes or documentation

No Comments

No Known Activations