INDEX

Explanations

predictions or assessments of probability regarding future occurrences

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

 likely

-0.87

 Likely

-0.81

Likely

-0.80

likely

-0.79

 étoit

-0.71

 étoient

-0.68



-0.68

Datuak

-0.67

 EconPapers

-0.67

 zijne

-0.66

POSITIVE LOGITS

kit

0.37

ten

0.36

jan

0.36

imo

0.35

hspace

0.33

edit

0.33

Ta

0.33

ta

0.33

note

0.33

item

0.32

Activations Density 0.003%

predictions or assessments of probability regarding future occurrences

No Comments

No Known Activations