INDEX

Explanations

mentions of "steps" in the context of processes 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

"])

-0.90

olesale

-0.83

}});

-0.81

tahankan

-0.80

ividual

-0.79

$_"

-0.78

"]}

-0.78

}}}

-0.78

]`

-0.77

 Barbier

-0.77

POSITIVE LOGITS

 step

2.85

Step

2.71

 Step

2.70

 STEP

2.64

step

2.60

 steps

2.45

STEP

2.32

 Steps

2.25

steps

2.08

Steps

2.05

Activations Density 0.047%

mentions of "steps" in the context of processes or instructions

No Comments

No Known Activations