INDEX

Explanations

terms related to stage productions or technical setups, particularly focusing on the concept of a "set."

oai_token-act-pair · gpt-3.5-turbo

phrases related to setups or arrangements 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ibly

-0.81

IBLE

-0.73

vernment

-0.70

ãĤĭ

-0.63

 Corps

-0.62

ocate

-0.62

loo

-0.61

anced

-0.58

 Authority

-0.58

 medial

-0.55

POSITIVE LOGITS

tle

1.19

upt

1.04

ter

1.00

chell

1.00

ters

0.99

ups

0.90

list

0.90

lists

0.88

Timeout

0.87

offs

0.87

Activations Density 0.050%

terms related to stage productions or technical setups, particularly focusing on the concept of a "set."

phrases related to setups or arrangements in various contexts

No Comments

No Known Activations