INDEX

Explanations

verbs that indicate actions taken by a subject in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 doInBackground

-0.94

 ligiloj

-0.93



-0.84

الحياه

-0.83

 defaultstate

-0.80

ValueStyle

-0.80

 EconPapers

-0.77

 autorytatywna

-0.76

ftagPool

-0.75

tagHelperRunner

-0.74

POSITIVE LOGITS

 together

0.64

 again

0.57

 directly

0.56

 straight

0.55

 separately

0.55

 slowly

0.54

 here

0.53

 steadily

0.53

 fiercely

0.53

 according

0.53

Activations Density 0.067%

verbs that indicate actions taken by a subject in a narrative context

No Comments

No Known Activations