INDEX

Explanations

words related to legal terms and locations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

twimg

-0.64

kasa

-0.52

ed

-0.51

principalTable

-0.50

 makeStyles

-0.48

yadi

-0.48

moud

-0.48

|()

-0.48

 Maulana

-0.48

harap

-0.48

POSITIVE LOGITS

 fath

0.94

 versace

0.94

 embra

0.92

 milf

0.92

 Euph

0.91

 peppa

0.89

 madonna

0.88

 verona

0.87

 archivio

0.86

 Pamph

0.86

Activations Density 0.235%

words related to legal terms and locations

No Comments

No Known Activations