INDEX

Explanations

technical terms or acronyms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "TA" in various contexts

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

papers

-0.85

space

-0.84

stocks

-0.79

lain

-0.72

nan

-0.72

sets

-0.71

espie

-0.68

nen

-0.68

ayn

-0.67

meyer

-0.67

POSITIVE LOGITS

pling

0.90

qua

0.86

BILITY

0.85

KE

0.84

uthor

0.83

uated

0.82

ZE

0.80

WA

0.78

pled

0.78

INA

0.77

Activations Density 0.029%

technical terms or acronyms

occurrences of the abbreviation "TA" in various contexts

No Comments

No Known Activations