INDEX

Explanations

adjectives related to the concept of looseness

oai_token-act-pair · gpt-3.5-turbo

the term "loose" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.82

HCR

-0.81

terday

-0.74

orea

-0.72

 GOODMAN

-0.71

aurus

-0.70

++++

-0.70

 Archdemon

-0.65

iop

-0.65

abeth

-0.64

POSITIVE LOGITS

leaf

1.09

 cannon

1.07

 ends

0.99

 Ends

0.96

 morals

0.92

 coupling

0.92

 cannons

0.87

fitting

0.85

cloth

0.84

luster

0.81

Activations Density 0.017%

adjectives related to the concept of looseness

the term "loose" in various contexts

No Comments

No Known Activations