INDEX

Explanations

terms related to classifications or categorizations 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berdayakan

-0.84

 MessageBoxIcon

-0.76

GrantedAuthority

-0.75

 auroit

-0.74

Jeografia

-0.71

piram

-0.70

 feroit

-0.70

ſelves

-0.68

 poffe

-0.67

 avoient

-0.67

POSITIVE LOGITS

0.77

↵↵

0.75

It

0.68

 More

0.66

The

0.66

In

0.65

For

0.64

As

0.61

No

0.61

If

0.60

Activations Density 0.090%

terms related to classifications or categorizations in various contexts

No Comments

No Known Activations