INDEX

Explanations

phrases or clauses that emphasize key descriptors or elements in a narrative

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

]-->

-0.58

oredCriteria

-0.54

msgTypes

-0.52

styleUrls

-0.49

ην

-0.49

 toluene

-0.48

 favoritas

-0.47

TintMode

-0.47

 fossils

-0.46

⁩

-0.46

POSITIVE LOGITS

 pesky

0.87

 elusive

0.78

 fameux

0.72

 dreaded

0.69

 extra

0.65

big

0.64

 aforementioned

0.62

esos

0.60

あの

0.59

 little

0.59

Activations Density 0.112%

phrases or clauses that emphasize key descriptors or elements in a narrative

No Comments

No Known Activations