INDEX

Explanations

instances of the term "makeText" associated with displaying messages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chymal

-0.50

িয়

-0.48

cfm

-0.48

uj

-0.47

فحة

-0.47

schirm

-0.45

orius

-0.45

 judíos

-0.44

reib

-0.44

 Fulton

-0.43

POSITIVE LOGITS

IMPORTED

2.32

AddTagHelper

1.52

makeText

1.44

sizeCache

1.07

 handleMessage

1.04

EDEFAULT

1.01

GeneratedMessage

0.99

IsContent

0.97

principalColumn

0.92

principalTable

0.91

Activations Density 0.011%

instances of the term "makeText" associated with displaying messages

No Comments

No Known Activations