INDEX

Explanations

years or decades

oai_token-act-pair · gpt-3.5-turbo

references to the decade of the 1980s

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

actor

-0.76

assic

-0.67

zag

-0.67

uden

-0.63

 agitation

-0.62

plom

-0.61

 incons

-0.60

 eclipse

-0.58

hess

-0.57

rog

-0.57

POSITIVE LOGITS

1.00

0.89

eenth

0.86

olver

0.85

0.80

dayName

0.79

%"

0.79

itement

0.78

Hz

0.77

swick

0.75

Activations Density 0.064%

years or decades

references to the decade of the 1980s

No Comments

No Known Activations