INDEX

Explanations

alphanumeric characters mixed with non-alphabetic symbols

oai_token-act-pair · gpt-3.5-turbo

references to computer programming or coding components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 necessities

-0.62

 mathemat

-0.61

iling

-0.61

 positives

-0.59

ãĥ¼ãĤ¯

-0.59

 loopholes

-0.59

 optimism

-0.57

 slump

-0.57

 unrem

-0.57

 compulsion

-0.57

POSITIVE LOGITS

;;;;;;;;;;;;

1.06

)))

1.05

 respectively

1.01

,,,,

1.00

"""

0.98

[/

0.97

,,

0.93

 âĵĺ

0.92

)),

0.92

etc

0.92

Activations Density 0.468%

alphanumeric characters mixed with non-alphabetic symbols

references to computer programming or coding components

No Comments

No Known Activations