INDEX

Explanations

programming constructs and data types

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

Code-related tokens: brackets, parentheses, quotes, and symbols

np_acts-logits-general · gemini-2.0-flash

closing brackets and parentheses

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

'}}

-0.84

"}}

-0.81

)')

-0.80

')))

-0.76

'))

-0.76

)"),

-0.75

)")

-0.75

')")

-0.75

)');

-0.73

')):

-0.71

POSITIVE LOGITS

1.53

].

1.34

],

1.30

1.18

];

1.17

.]

1.16

](

1.13

]:

1.12

!]

1.12

']

1.10

Activations Density 2.682%

programming constructs and data types

Code-related tokens: brackets, parentheses, quotes, and symbols

closing brackets and parentheses

No Comments

No Known Activations