INDEX

Explanations

terms related to "slam" or "slamming" in various contexts, particularly in sports or competitive scenarios

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

 Slam

-1.38

 slam

-1.13

Slam

-1.12

slam

-0.88

 slams

-0.73

 slamming

-0.68

Sla

-0.60

----</

-0.60

цездатний

-0.56

Sla

-0.54

POSITIVE LOGITS

PYX

0.41

BoxShadow

0.40

GEBURTSDATUM

0.40

hébergement

0.38

 héroe

0.38

segmented

0.36

 Morel

0.36

PullParser

0.34

pronounced

0.34

MethodManager

0.34

Activations Density 0.001%

terms related to "slam" or "slamming" in various contexts, particularly in sports or competitive scenarios

No Comments

No Known Activations