INDEX

Explanations

references to testing and hypotheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

клопе

-0.76

 Farina

-0.73

ankind

-0.69

 Backbone

-0.68

ORIAL

-0.68

Laptop

-0.67

ILIO

-0.66

Backbone

-0.65

SPIRE

-0.64

 kür

-0.64

POSITIVE LOGITS

 tests

1.64

 test

1.58

 Tests

1.54

 TEST

1.51

 testing

1.44

 Test

1.44

Tests

1.38

test

1.37

TEST

1.37

 tested

1.36

Activations Density 0.149%

references to testing and hypotheses

No Comments

No Known Activations