INDEX

Explanations

mentions of the word "acher" or variations such as "Bleacher" in the text

oai_token-act-pair · gpt-3.5-turbo

words related to teaching or educators

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

erest

-0.81

umbn

-0.76

pty

-0.76

ourced

-0.73

ality

-0.72

ported

-0.67

emn

-0.66

iting

-0.66

ERC

-0.65

ogyn

-0.64

POSITIVE LOGITS

jee

1.02

acher

0.85

berger

0.78

bilt

0.73

ãĤ·ãĥ£

0.72

baugh

0.70

door

0.69

ļéĨĴ

0.69

 =================================

0.68

otle

0.65

Activations Density 0.011%

mentions of the word "acher" or variations such as "Bleacher" in the text

words related to teaching or educators

No Comments

No Known Activations