INDEX

Explanations

evaluative terms related to quality and effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

antMatchers

-0.68

AutoresizingMask

-0.68

igurumi

-0.65

psack

-0.64

HomeAsUpEnabled

-0.63

CodedInputStream

-0.60

 TextEditing

-0.60

кумулятор

-0.59

ederos

-0.59

corollary

-0.59

POSITIVE LOGITS

Datuak

0.53

полу

0.53

su

0.46

 spirit

0.44

status

0.44

 halb

0.43

Result

0.43

Su

0.43

Status

0.42

 sula

0.41

Activations Density 0.429%

evaluative terms related to quality and effectiveness

No Comments

No Known Activations