INDEX

Explanations

distances and measurements expressed in numerical terms

oai_token-act-pair · gpt-3.5-turbo

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

ulate

-0.88

stal

-0.79

itative

-0.75

ulators

-0.75

SpaceEngineers

-0.74

icum

-0.73

 Rebell

-0.71

gio

-0.71

erd

-0.71

bean

-0.71

POSITIVE LOGITS

 travelled

1.17

 traveled

1.09

 distances

1.05

 distance

0.94

 separating

0.84

 between

0.82

 flung

0.80

 apart

0.77

 trave

0.75

finder

0.74

Activations Density 0.043%

distances and measurements expressed in numerical terms

No Comments

No Known Activations