INDEX

Explanations

mathematical or numerical terms, particularly focusing on linear concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to linear and exponential concepts or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

reon

-0.87

flies

-0.83

ardless

-0.75

bourg

-0.73

ittee

-0.72

rieving

-0.71

 Lauder

-0.71

ubs

-0.71

avering

-0.70

fw

-0.70

POSITIVE LOGITS

ization

1.09

ized

1.08

izable

0.97

ity

0.96

 accelerator

0.91

 algebra

0.91

ities

0.89

izes

0.88

 equations

0.85

 traject

0.84

Activations Density 0.019%

mathematical or numerical terms, particularly focusing on linear concepts

terms related to linear and exponential concepts or structures

No Comments

No Known Activations