INDEX

Explanations

sections of text that contain detailed statistical or scientific content

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

Image file names or paths

np_acts-logits-general · gemini-2.0-flash

image links and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 PrintWriter

-0.74

+#+#

-0.73

addPreferredGap

-0.66

 للمعارف

-0.66

 TextInputType

-0.62

IntoConstraints

-0.61

ArgsConstructor

-0.60

transQ

-0.60

CodeAttribute

-0.60

libft

-0.59

POSITIVE LOGITS

Untitled

0.83

 Untitled

0.68

Unnamed

0.61

untitled

0.59

 untitled

0.55

IndentedString

0.54

unnamed

0.53

 PicClick

0.49

 spit

0.49

giphy

0.49

Activations Density 0.184%

sections of text that contain detailed statistical or scientific content

Image file names or paths

image links and references

No Comments

No Known Activations