INDEX

Explanations

proper nouns or named entities

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'W' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 succeeding

-0.77

arial

-0.77

displayText

-0.73

 unpre

-0.70

 revived

-0.68

EStream

-0.67

 seiz

-0.65

illary

-0.65

milo

-0.65

 unarmed

-0.64

POSITIVE LOGITS

atts

1.19

ITNESS

1.15

edge

1.10

atson

1.07

OW

1.07

ashington

1.06

OOD

1.05

restling

1.05

itness

1.03

TF

1.00

Activations Density 0.042%

proper nouns or named entities

instances of the letter 'W' in various contexts

No Comments

No Known Activations