INDEX

Explanations

phrases that describe procedural steps or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

amet

-0.47

PRWEB

-0.47

cznych

-0.46

 sorted

-0.45

 dispersion

-0.45

veille

-0.45

 discours

-0.44

 dispersed

-0.44

 vila

-0.44

lastung

-0.44

POSITIVE LOGITS

 step

1.98

 steps

1.87

step

1.83

 Step

1.80

 Steps

1.78

Step

1.74

steps

1.67

 STEPS

1.66

 STEP

1.66

STEP

1.59

Activations Density 0.157%

phrases that describe procedural steps or instructions

No Comments

No Known Activations