INDEX

Explanations

instances where someone is being criticized or blamed for something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "for" 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

edin

-0.87

LAB

-0.81

fleet

-0.77

OTAL

-0.77

along

-0.76

atl

-0.74

 awaits

-0.74

nin

-0.74

oct

-0.72

hess

-0.72

POSITIVE LOGITS

 centuries

0.94

geries

0.94

gotten

0.93

gery

0.92

 example

0.90

 daring

0.89

 inaction

0.88

 decades

0.85

bidden

0.84

 awhile

0.83

Activations Density 0.142%

instances where someone is being criticized or blamed for something

occurrences of the word "for" in various contexts

No Comments

No Known Activations