INDEX

Explanations

symbols related to mathematical or scientific notation

oai_token-act-pair · gpt-3.5-turbo

the parameter symbols and notations typically associated with statistical or mathematical models

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

 Ples

-0.77

ESSION

-0.76

ividual

-0.75

 guiActiveUnfocused

-0.71

theless

-0.69

Downloadha

-0.69

Ì¶

-0.69

ãģį

-0.68

 Springs

-0.65

POSITIVE LOGITS

©

1.21

Ľ

1.04

¹

1.00

ł

0.99

³

0.99

ope

0.89

º

0.85

ĳ

0.84

£

0.83

Ķ

0.83

Activations Density 0.027%

symbols related to mathematical or scientific notation

the parameter symbols and notations typically associated with statistical or mathematical models

No Comments

No Known Activations