INDEX

Explanations

lists of items or entities

oai_token-act-pair · gpt-3.5-turbo

references to lists or enumerations of items

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

 Aber

-0.74

irgin

-0.69

 Thames

-0.64

 Gore

-0.63

 seas

-0.63

icago

-0.63

 Huck

-0.63

 Ratt

-0.59

 Abbey

-0.59

 trib

-0.59

POSITIVE LOGITS

erv

1.14

lists

0.87

lessly

0.84

abet

0.84

lessness

0.84

icles

0.83

uably

0.81

icle

0.79

Ã¶n

0.77

ening

0.77

Activations Density 0.032%

lists of items or entities

references to lists or enumerations of items

No Comments

No Known Activations