INDEX

Explanations

identifiers and references related to programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

TagMode

-0.55

 OMITBAD

-0.46

pla

-0.45

ok

-0.44

dir

-0.43

-0.42

 Will

-0.42

-0.41

POSITIVE LOGITS

uxxxx

0.81

 myſelf

0.78

ſelves

0.77

neſs

0.77

 ſind

0.77

StoryboardSegue

0.77

$_"

0.76

ſelf

0.76

 purpoſe

0.76

 poffible

0.75

Activations Density 0.089%

identifiers and references related to programming or data structures

No Comments

No Known Activations