INDEX

Explanations

descriptions of physical appearances and emotions tied to discomfort or grotesqueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<bos>

-0.61

or

-0.55

-0.54

 special

-0.53

 recently

-0.53

“

-0.51

 when

-0.48

for

-0.48

POSITIVE LOGITS

 itſelf

0.95

featureID

0.93

WireFormat

0.91

 initComponents

0.87

 ་་

0.81

 doubtnut

0.78

writeFieldEnd

0.77

 AssemblyCulture

0.75

новниш

0.74

 lenker

0.73

Activations Density 0.294%

descriptions of physical appearances and emotions tied to discomfort or grotesqueness

No Comments

No Known Activations