INDEX

Explanations

percentages

oai_token-act-pair · gpt-3.5-turbo

patterns of numerical data or statistics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 advis

-0.78

 homelessness

-0.76

 architectural

-0.76

 salty

-0.72

 aquatic

-0.71

 sustainability

-0.71

 proactive

-0.71

 bonded

-0.71

 traveler

-0.71

 ultras

-0.69

POSITIVE LOGITS

1.10

jpg

1.06

sbm

1.04

htm

1.03

0.99

jar

0.98

Downloadha

0.96

0.95

html

0.94

Activations Density 0.128%

percentages

patterns of numerical data or statistics

No Comments

No Known Activations