INDEX

Explanations

dates, particularly the year "2001"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the year 2001

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

accompan

-0.76

anch

-0.69

Nation

-0.69

ony

-0.68

rom

-0.68

romancer

-0.66

alling

-0.66

bon

-0.65

lying

-0.64

tics

-0.64

POSITIVE LOGITS

ĸļ

0.96

ãĥĥãĥī

0.87

-'

0.86

etics

0.74

sov

0.70

aru

0.69

ÙĨ

0.69

å¹

0.69

ãĥ³ãĤ¸

0.68

UFC

0.67

Activations Density 0.019%

dates, particularly the year "2001"

occurrences of the year 2001

No Comments

No Known Activations