INDEX

Explanations

proper nouns of specific individuals

oai_token-act-pair · gpt-3.5-turbo

names and references to notable individuals or entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

etheless

-0.96

rawdownloadcloneembedreportprint

-0.69

SHIP

-0.67

rontal

-0.61

Adjust

-0.61

 Alibaba

-0.61

Pear

-0.59

terday

-0.59

Edited

-0.59

VILLE

-0.59

POSITIVE LOGITS

Ã»

0.74

arde

0.71

Ã¡s

0.69

esi

0.69

Fem

0.65

 inclusive

0.62

isi

0.62

Ã³

0.61

 fatig

0.61

apo

0.60

Activations Density 0.307%

proper nouns of specific individuals

names and references to notable individuals or entities

No Comments

No Known Activations