INDEX

Explanations

words related to technology or brand names, particularly "Fusion."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Fusion" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ript

-0.75

 Ancients

-0.71

Org

-0.70

surv

-0.69

peer

-0.67

supp

-0.65

 Logged

-0.65

ODUCT

-0.64

obby

-0.62

graduate

-0.62

POSITIVE LOGITS

 Fusion

0.96

 fusion

0.89

 mash

0.74

ãĥ¼ãĤ¯

0.73

Jet

0.72

 bundles

0.70

ctions

0.70

ction

0.70

 spins

0.70

 capacitor

0.69

Activations Density 0.009%

words related to technology or brand names, particularly "Fusion."

mentions of "Fusion" in various contexts

No Comments

No Known Activations