INDEX

Explanations

acronyms consisting of two capital letters followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to specific codes or acronyms, particularly those that start with "EG."

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

ãĥīãĥ©ãĤ´ãĥ³

-0.90

itude

-0.74

ãĥĥãĤ¯

-0.72

Ã±o

-0.70

achus

-0.69

tenance

-0.69

thren

-0.67

ched

-0.65

ãĥ¼ãĥ³

-0.65

itia

-0.65

POSITIVE LOGITS

REG

0.93

BIT

0.85

LES

0.80

entric

0.79

ossip

0.78

ILE

0.78

ERG

0.77

LER

0.77

roups

0.77

IVERS

0.76

Activations Density 0.014%

acronyms consisting of two capital letters followed by a number

references to specific codes or acronyms, particularly those that start with "EG."

No Comments

No Known Activations