INDEX

Explanations

symbols and specific data notation in technical texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 esternos

-0.64

]--;

-0.63

Tikang

-0.62

RegressionTest

-0.62

})));

-0.61

ThroughAttribute

-0.61

 combineReducers

-0.61

évaluateur

-0.59

keyColumn

-0.57

Хьажоргаш

-0.55

POSITIVE LOGITS

=>

0.74

bn

0.69

sim

0.68

 href

0.63

asList

0.61

CJK

0.58

||

0.58

 Biol

0.57

sendRedirect

0.57

tiene

0.56

Activations Density 0.040%

symbols and specific data notation in technical texts

No Comments

No Known Activations