INDEX

Explanations

key actionable steps or commands in a technical context

oai_token-act-pair · gpt-3.5-turbo

actionable words or phrases related to tasks and instructions

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

.","

-0.59

 ..."

-0.56

 thereto

-0.55

 ï¿½

-0.54

''

-0.53

``(

-0.52

.ï¿½

-0.51

``

-0.50

 otherwise

-0.48

 âĢ¦"

-0.48

POSITIVE LOGITS

odore

0.87

resa

0.87

bidden

0.73

tymology

0.72

jamin

0.71

xiety

0.71

foundland

0.69

swers

0.69

cyclopedia

0.69

notations

0.68

Activations Density 0.705%

key actionable steps or commands in a technical context

actionable words or phrases related to tasks and instructions

No Comments

No Known Activations