INDEX

Explanations

names containing the string "Naz"

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals with the name "Naz" and their associated contexts

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

IVES

-0.76

ACTED

-0.73

IVE

-0.72

ENGTH

-0.71

ESSION

-0.70

lessly

-0.70

#$

-0.69

OME

-0.66

ANGE

-0.65

 boiling

-0.64

POSITIVE LOGITS

areth

1.31

imet

1.00

ril

0.98

emonic

0.97

oche

0.96

aji

0.94

Naz

0.93

dar

0.92

oid

0.90

ifa

0.89

Activations Density 0.016%

names containing the string "Naz"

mentions of individuals with the name "Naz" and their associated contexts

No Comments

No Known Activations