INDEX

Explanations

statements or references from sources as evidence or support

oai_token-act-pair · gpt-3.5-turbo

references or citations in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orld

-0.84

ipeg

-0.79

amination

-0.72

quer

-0.70

visors

-0.69

ifix

-0.69

vic

-0.68

sembly

-0.68

ct

-0.68

xy

-0.67

POSITIVE LOGITS

 citations

0.90

 warnings

0.87

 scriptures

0.77

 examples

0.75

 sources

0.74

 excuses

0.72

 citation

0.70

 citing

0.70

 unnamed

0.69

 quotes

0.67

Activations Density 0.037%

statements or references from sources as evidence or support

references or citations in a text

No Comments

No Known Activations