INDEX

Explanations

references to characters and their roles within 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 @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HttpFoundation

-0.59

zecz

-0.46

 ")");

-0.44

 milagro

-0.43

舺

-0.42

 Avent

-0.41

enteuer

-0.41

 Himo

-0.41

 wikihow

-0.40

AnchorTagHelper

-0.39

POSITIVE LOGITS

 evil

1.07

evil

0.92

 villain

0.87

 Evil

0.87

 tyrant

0.80

Evil

0.79

 sinister

0.79

 villains

0.78

 OMITBAD

0.77

 cack

0.77

Activations Density 0.324%

references to characters and their roles within a narrative context

No Comments

No Known Activations