INDEX

Explanations

words related to books, stories, seasons, campaigns, history, and events

oai_token-act-pair · gpt-3.5-turbo

references to books and historical narratives

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

 hint

-0.66

 interfering

-0.65

 nudity

-0.65

 diffuse

-0.63

 conve

-0.61

 Utilities

-0.60

 privately

-0.60

 inaccessible

-0.60

 hashing

-0.59

wa

-0.58

POSITIVE LOGITS

 accol

0.84

ably

0.82

eve

0.80

marks

0.79

Mission

0.77

icent

0.77

 medals

0.75

ends

0.74

Winner

0.73

 milestones

0.73

Activations Density 0.416%

words related to books, stories, seasons, campaigns, history, and events

references to books and historical narratives

No Comments

No Known Activations