INDEX

Explanations

the word "La"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "La" followed by numerical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

manship

-0.93

lessly

-0.90

Ö¼

-0.87

 sidx

-0.78

lessness

-0.73

PLIED

-0.69

flies

-0.68

yright

-0.67

ICLE

-0.67

cffff

-0.66

POSITIVE LOGITS

uren

1.07

vel

1.04

 Marse

0.99

TeX

0.95

ver

0.85

quire

0.85

very

0.84

vern

0.83

verty

0.82

Var

0.82

Activations Density 0.015%

the word "La"

mentions of the word "La" followed by numerical identifiers

No Comments

No Known Activations