INDEX

Explanations

positive and negative descriptive terms

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of surprise or unexpectedness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

FN

-0.67

Kik

-0.64

 Shepard

-0.64

 ---------

-0.63

 Naples

-0.63

 Leilan

-0.62

 Bret

-0.62

 Florence

-0.60

Nap

-0.60

 ãĤ

-0.59

POSITIVE LOGITS

1.02

"!

0.97

"],

0.93

"âĢ¦

0.92

terday

0.91

tainment

0.91

",

0.90

"]

0.90

":

0.90

usterity

0.86

Activations Density 0.229%

positive and negative descriptive terms

words related to the concept of surprise or unexpectedness

No Comments

No Known Activations