INDEX

Explanations

references to neo-related terms

oai_token-act-pair · gpt-3.5-turbo

references to neo-political ideologies

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

 ILCS

-0.87

ãĤ¼ãĤ¦ãĤ¹

-0.81

ORED

-0.78

hips

-0.77

channelAvailability

-0.76

loo

-0.76

lessly

-0.72

rooms

-0.72

REDACTED

-0.70

Interstitial

-0.69

POSITIVE LOGITS

ge

0.90

flex

0.81

forming

0.80

emer

0.77

fer

0.77

igen

0.75

emonic

0.75

neo

0.74

judicial

0.74

Activations Density 0.020%

references to neo-related terms

references to neo-political ideologies

No Comments

No Known Activations