INDEX

Explanations

instances where a specific number of items or individuals is mentioned within a context

oai_token-act-pair · gpt-3.5-turbo

references to groups of people or items

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

 Cosponsors

-0.71

 Santana

-0.70

 Nash

-0.66

 Held

-0.66

 Okawaru

-0.62

 Whitman

-0.62

 Stock

-0.62

 Bundy

-0.62

 Mans

-0.62

enment

-0.62

POSITIVE LOGITS

 deported

0.74

 involves

0.72

 sucked

0.71

 translates

0.70

 consisted

0.70

 succeeded

0.67

 entails

0.67

 involved

0.66

 constitutes

0.66

eah

0.65

Activations Density 0.074%

instances where a specific number of items or individuals is mentioned within a context

references to groups of people or items

No Comments

No Known Activations