INDEX

Explanations

occurrences of the word "to" in various contexts

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

migrationBuilder

-0.74

NOPQRST

-0.63

țe

-0.61

fsp

-0.59

 dataSnapshot

-0.59

ApiModelProperty

-0.58

consulté

-0.58

 numberOfRows

-0.58

Rè

-0.57

NewUrlParser

-0.57

POSITIVE LOGITS

 backs

0.60

 Back

0.60

Back

0.57

 back

0.55

backed

0.54

Backing

0.53

 BACK

0.52

BACK

0.52

 balik

0.51

 variétés

0.49

Activations Density 0.148%

occurrences of the word "to" in various contexts

No Comments

No Known Activations