INDEX

Explanations

mentions of the word "Ore"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "ore" in various contexts

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

":["

-0.71

enegger

-0.70

ilitating

-0.68

ivity

-0.68

tips

-0.63

 Shepard

-0.62

perture

-0.60

ulative

-0.60

BILITIES

-0.60

owler

-0.60

POSITIVE LOGITS

heim

0.94

gan

0.88

heimer

0.87

ghan

0.84

asure

0.78

lda

0.77

 mined

0.76

vine

0.75

aser

0.74

tha

0.74

Activations Density 0.046%

mentions of the word "Ore"

mentions of the term "ore" in various contexts

No Comments

No Known Activations