INDEX

Explanations

proper nouns related to specific individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly in the context of entertainment or sports

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

selage

-0.95

hammad

-0.83

accompan

-0.81

 Archdemon

-0.81

scape

-0.79

ãĤ¼ãĤ¦ãĤ¹

-0.79

orter

-0.75

nered

-0.74

cles

-0.73

illed

-0.73

POSITIVE LOGITS

 Fallon

0.92

IGH

0.76

odor

0.75

val

0.72

pton

0.68

 acid

0.67

 Bros

0.65

mont

0.63

URN

0.63

iod

0.63

Activations Density 0.020%

proper nouns related to specific individuals

mentions of specific individuals, particularly in the context of entertainment or sports

No Comments

No Known Activations