INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

names and references related to specific individuals and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

hammad

-0.90

antine

-0.78

usra

-0.78

ted

-0.75

lux

-0.72

icts

-0.70

¥µ

-0.68

dinand

-0.67

rained

-0.67

angelo

-0.67

POSITIVE LOGITS

pring

0.90

 Kers

0.82

 Hitch

0.78

 Seeds

0.75

ould

0.74

creen

0.73

alez

0.70

aceous

0.70

olitics

0.69

apers

0.69

Activations Density 0.026%

proper nouns and names

names and references related to specific individuals and their works

No Comments

No Known Activations