INDEX

Explanations

adjectives and nouns describing personal traits or characteristics

oai_token-act-pair · gpt-3.5-turbo

terms related to traits and characteristics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

endar

-0.80

endars

-0.75

source

-0.69

oner

-0.65

arger

-0.65

 GEAR

-0.64

ollo

-0.64

til

-0.63

lins

-0.61

aii

-0.60

POSITIVE LOGITS

 traits

1.15

 trait

1.00

hered

1.00

 characteristics

0.96

 characteristic

0.92

 qualities

0.88

 distinguishing

0.87

 predis

0.86

et

0.81

 attributes

0.81

Activations Density 0.095%

adjectives and nouns describing personal traits or characteristics

terms related to traits and characteristics

No Comments

No Known Activations