INDEX

Explanations

questions questioning motivation or justification behind actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ioutil

-0.49

||

-0.46

 vincere

-0.44

templateUrl

-0.43

 Dumas

-0.43

IsMutable

-0.42

Successfully

-0.41

andro

-0.40

MathML

-0.40

 diver

-0.40

POSITIVE LOGITS

djangoproject

0.74

 suddenly

0.71

 Insee

0.69

principalTable

0.69

 للمعارف

0.66

writeFieldEnd

0.66

suddenly

0.63

Зноскі

0.63

そんなに

0.62

ConstraintMaker

0.62

Activations Density 0.117%

questions questioning motivation or justification behind actions or statements

No Comments

No Known Activations