INDEX

Explanations

coordinates and positional information within a specified context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

tagHelperRunner

-0.69

 resourceCulture

-0.62

StructEnd

-0.60

منابع

-0.55

UVWXYZ

-0.50

alnız

-0.47

Personensuche

-0.47

 createSlice

-0.46

cinogenicity

-0.46

POSITIVE LOGITS

 coordinates

0.73

 Coordinates

0.69

 coords

0.64

 LatLng

0.63

<bos>

0.62

HasAnnotation

0.61

 coord

0.61

исленность

0.58

 Coord

0.57

Coords

0.57

Activations Density 0.569%

coordinates and positional information within a specified context

No Comments

No Known Activations