INDEX

Explanations

specific phrases or terms related to formal or structured discourse, particularly in the context of research or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

smithy

-0.43

<bos>

-0.42

 offerts

-0.39

 ruota

-0.38

突

-0.38

aw

-0.38

 cuire

-0.38

 percol

-0.36

 ouverts

-0.36

Roc

-0.35

POSITIVE LOGITS

writeFieldEnd

0.94

 يتيمه

0.79

complexContent

0.74

Tembelea

0.74

mergeFrom

0.69

umenter

0.69

mands

0.69

ighbor

0.67

jewództ

0.67

 doInBackground

0.67

Activations Density 1.177%

specific phrases or terms related to formal or structured discourse, particularly in the context of research or evaluations

No Comments

No Known Activations