INDEX

Explanations

Secure Elements (SE) followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term 'SE' followed by a number, indicating a specific product or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iasis

-0.96

ocrats

-0.77

gettable

-0.74

puff

-0.73

ificate

-0.72

lessly

-0.72

doms

-0.71

culosis

-0.71

cake

-0.70

bid

-0.68

POSITIVE LOGITS

ASON

1.16

VEN

1.10

VER

0.96

ATTLE

0.93

IU

0.91

ARCH

0.88

FR

0.85

BR

0.84

ATING

0.83

TERN

0.82

Activations Density 0.007%

Secure Elements (SE) followed by a numerical value

occurrences of the term 'SE' followed by a number, indicating a specific product or entity

No Comments

No Known Activations