INDEX

Explanations

sentences that convey strong opinions or conclusions, often expressed with emphasis

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

Må

-0.57

Conheça

-0.55

Apre

-0.53

 turi

-0.52

Zdra

-0.52

Vía

-0.51

Meto

-0.51

Pró

-0.50

Espa

-0.50

Conoce

-0.50

POSITIVE LOGITS

 unden

1.09

 suscep

1.07

 purcha

1.05

 lorenzo

1.05

<bos>

1.04

 nicolas

1.04

 jacques

1.02

 jorge

0.99

 increa

0.96

 tetrach

0.96

Activations Density 0.412%

sentences that convey strong opinions or conclusions, often expressed with emphasis

No Comments

No Known Activations