INDEX

Explanations

phrases that suggest uncertainty or possibility

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

Sentences starting with "Perhaps" or "Maybe"

np_acts-logits-general · gemini-2.0-flash

introducing a possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 presumably

-1.12

 probably

-1.06

 undoubtedly

-1.04

probably

-1.03

presumably

-1.02

 apparently

-0.99

 doubtless

-0.95

apparently

-0.94

 seguramente

-0.94

 Presumably

-0.94

POSITIVE LOGITS

 someday

0.98

 subconsciously

0.83

 jopa

0.77

 sogar

0.76

 even

0.74

 unintentionally

0.71

 unknowingly

0.70

 unconsciously

0.70

 some

0.70

 inadvertently

0.69

Activations Density 0.369%

phrases that suggest uncertainty or possibility

Sentences starting with "Perhaps" or "Maybe"

introducing a possibility

No Comments

No Known Activations