INDEX

Explanations

mentions of the word "rot" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "rot" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nect

-0.83

 EntityItem

-0.80

omething

-0.71

rahim

-0.66

ystem

-0.61

inez

-0.61

dress

-0.60

ynthesis

-0.59

 Countdown

-0.58

 TOTAL

-0.58

POSITIVE LOGITS

unda

1.21

ational

1.20

ations

1.19

oscope

1.04

atory

0.92

ife

0.88

omon

0.85

osc

0.85

ting

0.84

atile

0.84

Activations Density 0.046%

mentions of the word "rot" in various contexts

occurrences of the term "rot" and its variations

No Comments

No Known Activations