INDEX

Explanations

test-related phrases and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

aktery

-0.83

 Backbone

-0.76

ctility

-0.71

 quelcon

-0.70

hülle

-0.70

kijken

-0.70

 Farina

-0.69

 snippetHide

-0.69

nerie

-0.68

""".

-0.68

POSITIVE LOGITS

 tests

1.20

 test

1.11

 Test

1.10

 TEST

1.08

 Tests

1.06

test

1.05

Test

1.04

TEST

1.02

Tests

0.97

 TESTS

0.96

Activations Density 0.114%

test-related phrases and keywords

No Comments

No Known Activations