INDEX

Explanations

acronyms associated with official or formal terms, potentially related to organizations or classification systems

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "OP" indicating various operational contexts or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥīãĥ©ãĤ´ãĥ³

-0.88

 Lanka

-0.70

ãĥĨãĤ£

-0.70

perse

-0.68

Qi

-0.67

 Cantor

-0.65

 Sins

-0.65

ãģ®å®

-0.65

 Sabb

-0.65

taboola

-0.65

POSITIVE LOGITS

rompt

1.19

olicy

1.16

yright

1.15

rint

1.12

inion

1.08

etition

1.06

rodu

1.06

arent

1.06

TION

1.06

sych

1.03

Activations Density 0.013%

acronyms associated with official or formal terms, potentially related to organizations or classification systems

occurrences of the abbreviation "OP" indicating various operational contexts or documents

No Comments

No Known Activations