INDEX

Explanations

symbols and formatting marks associated with data structures or references

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

Code, file paths, or program instructions

np_acts-logits-general · gemini-2.0-flash

driving cars

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

 Monfieur

-0.96

 itſelf

-0.94

 leaſt

-0.91

 ſeveral

-0.87

 Houſe

-0.87

 diſt

-0.85

 leſs

-0.85

 raiſ

-0.83

 Theſe

-0.83

aimana

-0.83

POSITIVE LOGITS

</em>

0.88

</i>

0.79

/*

0.74

<em>

0.70

<i>

0.65

flex

0.62

 Casper

0.60

0.58

NLR

0.56

MessageTagHelper

0.56

Activations Density 0.164%

symbols and formatting marks associated with data structures or references

Code, file paths, or program instructions

driving cars

No Comments

No Known Activations