INDEX

Explanations

technical terminology related to programming errors and warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.91

ſelves

-0.90

expandindo

-0.88

الحياه

-0.87

LLocation

-0.84

ſelf

-0.84

 raiſ

-0.82

 unknownFields

-0.82

 themſelves

-0.81

uſ

-0.81

POSITIVE LOGITS

</i>

0.54

...

0.47

 properly

0.46

0.45

dataIndex

0.44

 Properly

0.44

0.43

ssis

0.42

Activations Density 0.435%

technical terminology related to programming errors and warnings

No Comments

No Known Activations