INDEX

Explanations

elements related to structural formatting in documentation or data representation

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

Text within square brackets

np_acts-logits-general · gemini-2.0-flash

bracketed labels or annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

"})

-0.83

"))

-0.83

{}",

-0.83

)")

-0.76

)')

-0.76

')}}

-0.74

')))

-0.74

"});

-0.71

)))

-0.70

'))

-0.69

POSITIVE LOGITS

![

1.12

 }^{[

1.07

$[\

1.03

“[

0.94

+][

0.93

 quæ

0.92

$[

0.90

{[

0.90

$[-

0.88

..]

0.83

Activations Density 0.881%

elements related to structural formatting in documentation or data representation

Text within square brackets

bracketed labels or annotations

No Comments

No Known Activations