INDEX

Explanations

words related to inquiries and investigations

oai_token-act-pair · gpt-3.5-turbo

words related to inquiries or investigations

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

enburg

-0.62

 Depend

-0.61

stead

-0.61

 Beet

-0.61

har

-0.60

birth

-0.59

liners

-0.58

alone

-0.58

 Accord

-0.57

éĹĺ

-0.57

POSITIVE LOGITS

 probing

1.10

 inquire

1.09

 inqu

1.05

naires

1.04

iry

1.02

iries

0.99

isition

0.99

 into

0.96

 questions

0.94

into

0.89

Activations Density 0.066%

words related to inquiries and investigations

words related to inquiries or investigations

No Comments

No Known Activations