INDEX

Explanations

the acronym 'A'

oai_token-act-pair · gpt-3.5-turbo

references to the letter 'A' 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enegger

-0.95

lasses

-0.71

ãĤ©

-0.67

 unders

-0.65

eners

-0.61

cards

-0.59

 WATCHED

-0.58

 Bigfoot

-0.58

yi

-0.58

offer

-0.58

POSITIVE LOGITS

BILITY

1.27

qua

1.23

verages

1.13

BILITIES

1.07

HAHA

1.04

chieve

1.03

VE

1.03

HA

1.02

UTH

1.00

ircraft

1.00

Activations Density 0.053%

the acronym 'A'

references to the letter 'A' in various contexts

No Comments

No Known Activations