INDEX

Explanations

terms related to lenses and lensing in scientific contexts

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

 lent

-0.91

 Lent

-0.90

 Lenti

-0.82

len

-0.80

 lenti

-0.78

Len

-0.75

Len

-0.73

lent

-0.72

LEN

-0.69

Lens

-0.69

POSITIVE LOGITS

 Schlegel

0.38

もん

0.33

inger

0.33

neighborhood

0.30

 harta

0.30

gods

0.30

lapsing

0.30

 Wachs

0.30

Resumen

0.30

 ingres

0.30

Activations Density 0.010%

terms related to lenses and lensing in scientific contexts

No Comments

No Known Activations