INDEX

Explanations

Times and dates indicated by slashes (e.g., "6/8" or "15/43")

oai_token-act-pair · gpt-3.5-turbo

specific references to media sources and publication events

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

 Cary

-0.65

 Burgess

-0.64

 Fletcher

-0.63

IPM

-0.62

 chop

-0.62

 merchants

-0.61

kson

-0.61

 carpet

-0.59

mie

-0.59

 idol

-0.59

POSITIVE LOGITS

AFP

0.87

Getty

0.84

pmwiki

0.80

Az

0.77

Sham

0.76

CBC

0.75

âĹ¼

0.75

Nar

0.73

Art

0.73

EVA

0.73

Activations Density 0.026%

Times and dates indicated by slashes (e.g., "6/8" or "15/43")

specific references to media sources and publication events

No Comments

No Known Activations