INDEX

Explanations

words related to processes or actions

oai_token-act-pair · gpt-3.5-turbo

gerunds and participles related to actions 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iness

-0.83

ascript

-0.83

nery

-0.83

bench

-0.81

mere

-0.81

talk

-0.81

deal

-0.80

Ã¨re

-0.78

cellence

-0.78

isma

-0.77

POSITIVE LOGITS

 agents

0.87

 platforms

0.81

 technologies

0.78

 alcoholic

0.76

 engagements

0.76

 professions

0.75

 substances

0.75

 sectors

0.73

tons

0.72

 edge

0.72

Activations Density 0.291%

words related to processes or actions

gerunds and participles related to actions in various contexts

No Comments

No Known Activations