INDEX

Explanations

acronyms or codes, such as 'SW' followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

specific identifiers or labels associated with software or systems

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

staking

-0.76

jury

-0.73

ãĤ¶

-0.73

ãĤ¹ãĥĪ

-0.71

uate

-0.70

sei

-0.68

gered

-0.67

ographed

-0.66

uated

-0.65

historic

-0.65

POSITIVE LOGITS

IFT

1.14

TOR

1.11

ITCH

1.11

SW

0.99

SL

0.95

OW

0.94

ESH

0.91

rup

0.91

ING

0.90

ED

0.88

Activations Density 0.024%

acronyms or codes, such as 'SW' followed by a numerical value

specific identifiers or labels associated with software or systems

No Comments

No Known Activations