INDEX

Explanations

names with "Wid" or "Tud", possibly last names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and locations

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

è¦ļéĨĴ

-0.76

 retaliate

-0.68

 Leban

-0.68

 compr

-0.64

 Collider

-0.62

IZE

-0.62

pmwiki

-0.60

 residual

-0.60

 tune

-0.60

ãĥĺ

-0.59

POSITIVE LOGITS

gets

1.18

ows

1.06

owed

0.94

erer

0.90

artz

0.82

nesday

0.81

Wid

0.80

ening

0.79

NT

0.79

erers

0.77

Activations Density 0.028%

names with "Wid" or "Tud", possibly last names

proper nouns, particularly names of individuals and locations

No Comments

No Known Activations