INDEX

Explanations

phrases related to research methodology and definitions

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

Text followed by citations or references

np_acts-logits-general · gemini-2.0-flash

see more links

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

الحياه

-0.64

subpackage

-0.61

/**

-0.61

UserScript

-0.58

 AssemblyTitle

-0.56

ashions

-0.56

+:+

-0.55

 propOrder

-0.55

Gemeinden

-0.55

principalTable

-0.54

POSITIVE LOGITS

 Click

1.06

詳しくは

1.04

 click

1.02

See

1.00

Click

0.98

See

0.94

see

0.94

see

0.94

 read

0.93

click

0.91

Activations Density 0.561%

phrases related to research methodology and definitions

Text followed by citations or references

see more links

No Comments

No Known Activations