INDEX

Explanations

verbs that imply causation or effect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.58

 utafitiHapana

-0.55

 takiego

-0.55

 indemnity

-0.54

 kurtka

-0.52

 damska

-0.52

 bourgeoisie

-0.51

BnF

-0.51

 reconstituted

-0.50

ggior

-0.49

POSITIVE LOGITS

руя

0.73

 thereby

0.72

 thus

0.69

SequentialGroup

0.69

OGND

0.67

Dabei

0.65

DECREF

0.64

lapsingToolbar

0.63

resulting

0.61

elyn

0.59

Activations Density 0.340%

verbs that imply causation or effect

No Comments

No Known Activations

verbs that imply causation or effect

No Comments

No Known Activations