INDEX

Explanations

terms related to energy and its various applications or technologies

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

The token "em" followed by other letters

np_acts-logits-general · gemini-2.0-flash

em prefix

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

 gynhyrchwyd

-1.01

CodeAttribute

-0.93

Referanser

-0.81

UnitTesting

-0.79

WaitGroup

-0.78

LEncoder

-0.75

Enllaços

-0.75

 Audiodateien

-0.74

jupiter

-0.74

SuppressMessage

-0.73

POSITIVE LOGITS

Em

1.01

em

0.90

Emb

0.87

EM

0.87

EM

0.87

EMB

0.86

Em

0.85

Emb

0.82

em

0.75

Emm

0.65

Activations Density 0.120%

terms related to energy and its various applications or technologies

The token "em" followed by other letters

em prefix

No Comments

No Known Activations