INDEX

Explanations

phrases related to individual agency or actions taken independently

oai_token-act-pair · gpt-3.5-turbo

instances of the word "themselves."

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

pour

-0.74

 Derby

-0.73

ammy

-0.72

rise

-0.71

von

-0.65

mare

-0.65

yip

-0.64

ulu

-0.64

 Surge

-0.64

grade

-0.64

POSITIVE LOGITS

 selves

1.06

selves

1.04

 underwater

0.78

pecially

0.77

 creatively

0.72

 respective

0.71

 themselves

0.71

 fict

0.70

BOOK

0.70

å

0.70

Activations Density 0.037%

phrases related to individual agency or actions taken independently

instances of the word "themselves."

No Comments

No Known Activations