INDEX

Explanations

terms related to scale or size

oai_token-act-pair · gpt-3.5-turbo

complex and technical language relating to various fields or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

$$$$

-0.72

 tremend

-0.69

 DRAG

-0.65

è£ħ

-0.65

GD

-0.65

peg

-0.65

 Kirin

-0.64

 è£ı

-0.59

 buck

-0.59

FN

-0.58

POSITIVE LOGITS

atic

1.03

atically

1.03

itionally

1.01

ologically

1.00

hetically

0.95

iminary

0.93

alities

0.91

inarily

0.90

ational

0.89

urgical

0.89

Activations Density 0.208%

terms related to scale or size

complex and technical language relating to various fields or concepts

No Comments

No Known Activations