INDEX

Explanations

specific numeric mentions not related to the content of the documents

oai_token-act-pair · gpt-3.5-turbo

numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 fert

-0.79

 manif

-0.78

 challeng

-0.77

 administr

-0.77

 newsp

-0.76

 symp

-0.71

 leve

-0.71

 respons

-0.70

 brid

-0.69

 proble

-0.69

POSITIVE LOGITS

 SHARES

1.10

 ILCS

1.04

 Explicit

0.89

 Hours

0.87

å¹

0.82

HOU

0.81

 Minutes

0.81

NCT

0.80

Activations Density 0.080%

specific numeric mentions not related to the content of the documents

numerical values or statistics

No Comments

No Known Activations