INDEX

Explanations

indicators of job listing details

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

sidemargin

-0.37

ab

-0.36

 shore

-0.35

 staff

-0.34

 easy

-0.34

ToOne

-0.32

 movement

-0.32

or

-0.32

 oasis

-0.32

helves

-0.31

POSITIVE LOGITS

AndEndTag

0.70

RTEE

0.63

 defaultstate

0.59

 kasarigan

0.55

 informée

0.54

atoare

0.54

ɵɵelementStart

0.54

 bailarina

0.52

toHaveBeenCalled

0.51

 colombiano

0.50

Activations Density 0.010%

indicators of job listing details

No Comments

No Known Activations