INDEX

Explanations

names or terms related to a specific word - "Ore."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Ore" and its context within the document

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

ivity

-0.93

ibility

-0.89

ible

-0.85

 ILCS

-0.76

ibly

-0.74

iveness

-0.73

orously

-0.72

ively

-0.70

orses

-0.70

ership

-0.69

POSITIVE LOGITS

nance

0.88

nz

0.85

gon

0.83

gas

0.77

bro

0.75

heim

0.75

 tremend

0.74

pillar

0.72

VEL

0.72

xia

0.71

Activations Density 0.109%

names or terms related to a specific word - "Ore."

mentions of the term "Ore" and its context within the document

No Comments

No Known Activations