INDEX

Explanations

occurrences of programming-related syntax and definitions in the text

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

Code or path-like strings

np_acts-logits-general · gemini-2.0-flash

programming language keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

he

-0.70

-0.68

-0.66

-0.65

the

-0.65

-0.64

in

-0.64

ho

-0.63

POSITIVE LOGITS

 pleaſure

1.09

 ſche

0.99

 cauſe

0.97

 houſe

0.97

 ſch

0.97

 "..\..\

0.96

 purpoſe

0.96

 "..\..\..\

0.94

 deſt

0.92

 ſtate

0.92

Activations Density 1.048%

occurrences of programming-related syntax and definitions in the text

Code or path-like strings

programming language keywords

No Comments

No Known Activations