INDEX

Explanations

phrases or words related to graphs and graphical representation

oai_token-act-pair · gpt-3.5-turbo

references to graphical representations or diagrams

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

 charity

-0.69

nuts

-0.65

 Ambrose

-0.64

 tradem

-0.63

ONT

-0.63

uders

-0.62

 Lomb

-0.61

aneous

-0.61

estinal

-0.61

 Idol

-0.60

POSITIVE LOGITS

ically

1.09

ical

0.85

ynt

0.85

graph

0.81

alogy

0.81

ite

0.80

iq

0.80

ql

0.79

ophone

0.77

oline

0.74

Activations Density 0.018%

phrases or words related to graphs and graphical representation

references to graphical representations or diagrams

No Comments

No Known Activations