INDEX

Explanations

comparative adjectives that suggest ranking or superiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

حياته

-0.60

Also

-0.58

also

-0.56

DebuggerNonUser

-0.56

 also

-0.54

Obrázky

-0.53

-0.52

Tazama

-0.52

Также

-0.52

AddHtmlAttribute

-0.51

POSITIVE LOGITS

 siquiera

0.91

binaan

0.79

 half

0.75

 barely

0.66

 halfway

0.64

 remotely

0.63

 attempt

0.61

 bother

0.60

 even

0.60

ScreenState

0.58

Activations Density 0.089%

comparative adjectives that suggest ranking or superiority

No Comments

No Known Activations