INDEX

Explanations

terms related to features or attributes of objects

oai_token-act-pair · gpt-3.5-turbo

topics related to identity and qualities of objects or substances

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

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

lees

-1.06

casts

-1.00

iddles

-0.94

builders

-0.90

boards

-0.89

stories

-0.88

sites

-0.87

bats

-0.86

reports

-0.85

bots

-0.85

POSITIVE LOGITS

 standpoint

1.16

 regimen

1.08

 combination

1.07

 proposition

1.06

 mixture

1.06

 arrangement

1.05

 solution

1.02

 affair

0.99

 entity

0.98

 foothold

0.98

Activations Density 0.548%

terms related to features or attributes of objects

topics related to identity and qualities of objects or substances

No Comments

No Known Activations