INDEX

Explanations

phrases that indicate uncertainty or speculation

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

Tokens after commas

np_acts-logits-general · gemini-2.0-flash

parts of code or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 mandatario

-0.57

 Çünkü

-0.53

Especially

-0.53

 Особенно

-0.52

 Especially

-0.52

 bởi

-0.49

 obstante

-0.49



-0.49

 umgekehrt

-0.48

moveToFirst

-0.47

POSITIVE LOGITS

 capable

0.93

 designed

0.87

 whose

0.86

SourceChecksum

0.84

 reminiscent

0.80

 resembling

0.77

 which

0.76

 modelled

0.74

whose

0.74

 intended

0.74

Activations Density 0.441%

phrases that indicate uncertainty or speculation

Tokens after commas

parts of code or definitions

No Comments

No Known Activations