INDEX

Explanations

mentions of specific visa types and related technical terms

oai_token-act-pair · gpt-3.5-turbo

references to specific numerical codes or identifiers

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

agna

-0.78

inventoryQuantity

-0.73

enegger

-0.72

inen

-0.71

 damned

-0.64

retch

-0.62

itri

-0.62

 guiActiveUn

-0.62

oooooooooooooooo

-0.61

uphem

-0.61

POSITIVE LOGITS

+,

0.84

xual

0.83

DM

0.83

XX

0.78

FY

0.76

nces

0.75

0.72

HB

0.71

+.

0.71

Gs

0.70

Activations Density 0.052%

mentions of specific visa types and related technical terms

references to specific numerical codes or identifiers

No Comments

No Known Activations