INDEX

Explanations

phrases related to specific names, particularly "Robbie"

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those related to sports or specific events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

igators

-0.81

nesia

-0.78

ngth

-0.72

ainment

-0.72

OA

-0.70

gor

-0.70

ure

-0.68

aternity

-0.68

igator

-0.67

ebin

-0.67

POSITIVE LOGITS

McF

0.91

 Robbie

0.82

eatures

0.76

 McKenzie

0.72

ggles

0.72

 Keane

0.67

eco

0.67

 Lowe

0.66

 Thomson

0.66

elsius

0.65

Activations Density 0.024%

phrases related to specific names, particularly "Robbie"

names of individuals, particularly those related to sports or specific events

No Comments

No Known Activations