INDEX

Explanations

the word "try" and its variations indicating attempts or experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 exponentially

-0.61

éges

-0.59

بوابة

-0.56

fuge

-0.54

깥

-0.52

 unconditional

-0.52

 للاسماء

-0.51

⋱

-0.50

 sovereignty

-0.50

tehenden

-0.50

POSITIVE LOGITS

 tried

1.03

 cues

0.92

try

0.92

Try

0.88

fit

0.86

fit

0.85

Try

0.85

cue

0.84

Tried

0.83

 Tried

0.83

Activations Density 0.096%

the word "try" and its variations indicating attempts or experiments

No Comments

No Known Activations