INDEX

Explanations

terms related to initial conditions or statements in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ultimately

-0.72

finally

-0.67

 دیکھیے

-0.64

 finally

-0.64

 незавершена

-0.64

previously

-0.63

 lastly

-0.63

 finalement

-0.62

 previously

-0.61

 uiteindelijk

-0.61

POSITIVE LOGITS

izers

0.72

 idea

0.66

 intent

0.66

 intention

0.65

 заду

0.64

 thought

0.63

 purpose

0.62

izations

0.61

idea

0.58

intended

0.57

Activations Density 0.188%

terms related to initial conditions or statements in a narrative context

No Comments

No Known Activations