INDEX

Explanations

elements related to application programming and medical research references

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

HTML or code-related text

np_acts-logits-general · gemini-2.0-flash

specific continuations

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

-1.17

-1.09

-1.04

-0.98

the

-0.98

in

-0.96

↵↵

-0.94

POSITIVE LOGITS

 незавершена

1.66

ſelf

1.62

تقاوى

1.62

 ſind

1.59

 متعلقه

1.58

 Anſ

1.57

 ſche

1.56

 houſe

1.55

 Мексичка

1.54

extAlignment

1.51

Activations Density 1.370%

elements related to application programming and medical research references

HTML or code-related text

specific continuations

No Comments

No Known Activations