INDEX

Explanations

instances of the letter 'H' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ―――――

-0.89

 viſ

-0.84

 ་་

-0.82

 verſ

-0.80

 ſever

-0.80

 ſind

-0.78

 myſelf

-0.77

 themſelves

-0.76

 ſeveral

-0.76

 Venkates

-0.73

POSITIVE LOGITS

2.11

1.78

1.49

setH

1.39

rH

1.32

xH

1.10

mH

1.06

cH

1.06

1.03

Activations Density 0.136%

instances of the letter 'H' in various contexts

No Comments

No Known Activations