INDEX

Explanations

statements indicating possibilities or hints of future occurrences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "may."

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

 Fighter

-0.70

ocracy

-0.68

performing

-0.66

ging

-0.66

 Enforcement

-0.65

 Constant

-0.64

feeding

-0.63

efeated

-0.62

raint

-0.62

zeb

-0.62

POSITIVE LOGITS

onna

1.03

hap

0.89

bes

0.87

 misunder

0.85

be

0.84

 someday

0.81

 derive

0.80

haps

0.79

NF

0.77

 feas

0.76

Activations Density 0.073%

statements indicating possibilities or hints of future occurrences

occurrences of the word "may."

No Comments

No Known Activations