INDEX

Explanations

references to active or ongoing actions or states

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

 leksikon

-0.52

LError

-0.46

QUADS

-0.45

Jose

-0.45

Borrar

-0.44

cupa

-0.44

enada

-0.44

ositol

-0.44

string

-0.43

José

-0.43

POSITIVE LOGITS

 ACTIVE

1.27

 active

1.21

 Active

1.19

 actives

1.14

active

1.11

 intersper

1.06

Active

1.05

 Inactive

1.04

 depic

1.04

ACTIVE

0.99

Activations Density 0.065%

references to active or ongoing actions or states

No Comments

No Known Activations