INDEX

Explanations

repeated articles and determiners in the text

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

quelize

-0.54

tvguidetime

-0.47

 intptr

-0.45

DMETHOD

-0.43

 costi

-0.40

 surla

-0.39

unisex

-0.39

îtra

-0.39

 maquiagem

-0.37

windig

-0.36

POSITIVE LOGITS

protoc

0.46

 CreateTagHelper

0.43

Distinctions

0.42

InSection

0.40

ycznie

0.38

+#+

0.37

 cojín

0.36

########.

0.36

原始内容存档于

0.36

ęku

0.36

Activations Density 0.010%

repeated articles and determiners in the text

No Comments

No Known Activations