INDEX

Explanations

references to numerical data, particularly the number three

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

MessageTagHelper

-0.69

ten

-0.68

 nine

-0.67

 five

-0.65

 four

-0.64

 three

-0.62

six

-0.61

 seven

-0.60



-0.59

 autorytatywna

-0.58

POSITIVE LOGITS

Two

2.02

 Three

1.99

Two

1.90

Three

1.87

 Four

1.63

Four

1.62

Five

1.41

Six

1.41

 Five

1.40

Six

1.35

Activations Density 0.263%

references to numerical data, particularly the number three

No Comments

No Known Activations