INDEX

Explanations

references to loss, mourning, and expressions of sympathy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 referenties

-0.54

lesse

-0.53

Bog

-0.49

letin

-0.48

zzá

-0.48

 bör

-0.47

zur

-0.46

 select

-0.46

virons

-0.45

POSITIVE LOGITS

 Himo

0.74

rrggbb

0.63

 NSCoder

0.61

 getItemCount

0.61

MigrationBuilder

0.59

stateMutability

0.59

 trajets

0.58

HomeAsUpEnabled

0.57

 GetEnumerator

0.57

Život

0.57

Activations Density 0.081%

references to loss, mourning, and expressions of sympathy

No Comments

No Known Activations