INDEX

Explanations

data formatting patterns capturing specific information in a structured document

oai_token-act-pair · gpt-3.5-turbo

numerical data or identifiers associated with entities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 eleph

-1.11

aditional

-0.94

ortunately

-0.85

Þ

-0.82

ò

-0.78

Ē

-0.73

ý

-0.73

ß

-0.73

ñ

-0.73

ø

-0.73

POSITIVE LOGITS

ovember

0.76

ageddon

0.71

yssey

0.70

Merit

0.64

amac

0.60

uers

0.60

ml

0.59

Aug

0.58

EngineDebug

0.58

daq

0.57

Activations Density 0.054%

data formatting patterns capturing specific information in a structured document

numerical data or identifiers associated with entities or events

No Comments

No Known Activations