INDEX

Explanations

names or terms related to people or places

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Gy" in various 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

éĹĺ

-0.93

ortium

-0.84

 Hurricanes

-0.83

 Archdemon

-0.83

IBLE

-0.77

ACTED

-0.75

 Dragonbound

-0.75

ãģ®éŃĶ

-0.72

 totality

-0.71

 reversible

-0.69

POSITIVE LOGITS

psy

1.24

Gy

1.17

gy

0.98

vette

0.97

rosc

0.94

Gy

0.91

romy

0.89

nec

0.88

rology

0.85

hett

0.84

Activations Density 0.009%

names or terms related to people or places

mentions of the term "Gy" in various contexts

No Comments

No Known Activations