INDEX

Explanations

phrases related to specific topics or fields, such as "area of expertise" or "area of concern"

oai_token-act-pair · gpt-3.5-turbo

phrases that denote specific domains or categories of expertise

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

 guiActive

-0.93

 Picks

-0.76

aciously

-0.66

wt

-0.65

pps

-0.64

wives

-0.63

advertisement

-0.63

soDeliveryDate

-0.63

frog

-0.63

uristic

-0.62

POSITIVE LOGITS

 expertise

0.85

 specialization

0.83

 specificity

0.80

 overlap

0.80

 contention

0.78

 interest

0.76

 weakness

0.76

 accommodation

0.74

 refinement

0.74

 deprivation

0.73

Activations Density 0.080%

phrases related to specific topics or fields, such as "area of expertise" or "area of concern"

phrases that denote specific domains or categories of expertise

No Comments

No Known Activations