INDEX

Explanations

names or references to specific people

oai_token-act-pair · gpt-3.5-turbo

the letter 'a'

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

lasses

-0.75

ARGET

-0.69

ymm

-0.68

<[

-0.67

pter

-0.67

aturdays

-0.66

ONSORED

-0.65

ometimes

-0.63

 glim

-0.63

OW

-0.62

POSITIVE LOGITS

Ã±

1.09

BILITY

0.93

Ã°

0.92

qua

0.90

Ã±a

0.90

ption

0.90

ichi

0.87

usterity

0.86

ishi

0.85

wn

0.85

Activations Density 0.063%

names or references to specific people

the letter 'a'

No Comments

No Known Activations