INDEX

Explanations

numbers related to measurements

oai_token-act-pair · gpt-3.5-turbo

notations related to measurements or values associated with units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Carlton

-0.71

 Loki

-0.69

nod

-0.67

 Starr

-0.67

 Reconstruction

-0.66

ļéĨĴ

-0.66

 Answers

-0.65

 bubbles

-0.64

 Edgar

-0.64

 Telegram

-0.64

POSITIVE LOGITS

etc

1.11

hr

1.04

each

0.97

0.96

oct

0.93

UV

0.91

RES

0.91

hour

0.89

USD

0.89

AU

0.88

Activations Density 0.038%

numbers related to measurements

notations related to measurements or values associated with units

No Comments

No Known Activations