INDEX

Explanations

names and terms related to the "Kol" entity

oai_token-act-pair · gpt-3.5-turbo

references to specific names or entities, particularly those associated with "Kol."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

llan

-0.83

ansion

-0.74

yre

-0.74

erness

-0.73

xe

-0.72

ires

-0.71

Services

-0.69

ll

-0.69

ylum

-0.69

POSITIVE LOGITS

obyl

0.75

opal

0.73

 Cecil

0.73

Kol

0.72

Uz

0.71

utonium

0.69

laus

0.69

lass

0.68

nic

0.67

 fitt

0.67

Activations Density 0.034%

names and terms related to the "Kol" entity

references to specific names or entities, particularly those associated with "Kol."

No Comments

No Known Activations