INDEX

Explanations

names or references to a specific person named Ron

oai_token-act-pair · gpt-3.5-turbo

references to the name "Ron"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

td

-0.63

 Pixie

-0.61

alam

-0.61

EMP

-0.60

 completion

-0.60

hower

-0.59

 Corpus

-0.58

uated

-0.58

 magnitude

-0.56

rhy

-0.56

POSITIVE LOGITS

aldo

1.09

ald

1.08

nie

1.00

ny

0.97

 Weasley

0.89

izont

0.89

 Swanson

0.88

igan

0.86

Paul

0.86

atics

0.85

Activations Density 0.016%

names or references to a specific person named Ron

references to the name "Ron"

No Comments

No Known Activations