INDEX

Explanations

mentions of sequences or sequences in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

TargetException

-0.77

WebVitals

-0.75

ioutil

-0.73

yntaxException

-0.72

BufferException

-0.69

mybatisplus

-0.69

RetentionPolicy

-0.68

reportWebVitals

-0.67

`,

-0.67

 ioutil

-0.65

POSITIVE LOGITS

 sequence

0.87

 inhibition

0.73

 sequences

0.61

hibitions

0.61

 Sequence

0.61

 Inhibition

0.59

 distinct

0.59

sequence

0.58

 else

0.57

 inhibitor

0.56

Activations Density 0.248%

mentions of sequences or sequences in data analysis

No Comments

No Known Activations