INDEX

Explanations

key terms related to scientific studies or evidence in a formal context

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

SharedCtor

-0.54

ьаж

-0.49

 Meksiku

-0.48

ValueStyle

-0.46

 chi̍t

-0.46

aarrggbb

-0.44

 становника

-0.44

:✨

-0.43

tagHelperRunner

-0.42

AutoScaleMode

-0.42

POSITIVE LOGITS

鑓

0.47

੝

0.47

SequentialGroup

0.45

gink

0.42

 vacu

0.41

 Constraints

0.40

 Judges

0.40

retra

0.39

BagConstraints

0.39

 Respondents

0.39

Activations Density 0.201%

key terms related to scientific studies or evidence in a formal context

No Comments

No Known Activations