INDEX

Explanations

names of specific locations and entities

oai_token-act-pair · gpt-3.5-turbo

geographic locations or entities

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

rencies

-0.78

schild

-0.70

 Canaver

-0.69

wagen

-0.68

ynthesis

-0.68

 centrif

-0.68

akable

-0.66

 Nasa

-0.66

 Bild

-0.66

 istg

-0.65

POSITIVE LOGITS

 County

1.09

 Legislature

0.94

 mayoral

0.93

 Tribune

0.93

 City

0.90

burgh

0.89

 Municipal

0.87

town

0.87

VILLE

0.87

unicip

0.87

Activations Density 0.379%

names of specific locations and entities

geographic locations or entities

No Comments

No Known Activations