INDEX

Explanations

phrases related to changes in a story or situation

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases indicating significant changes or shifts in circumstances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 Recomm

-0.89

 Cheong

-0.81

wikipedia

-0.74

pas

-0.69

oided

-0.68

enez

-0.67

Ans

-0.66

ETF

-0.65

ansas

-0.65

 tapes

-0.64

POSITIVE LOGITS

 toll

1.46

 turn

1.05

 tumble

0.98

 beating

0.96

 downturn

0.96

 pounding

0.95

 twist

0.95

 dive

0.91

hit

0.89

turn

0.89

Activations Density 0.074%

phrases related to changes in a story or situation

phrases indicating significant changes or shifts in circumstances

No Comments

No Known Activations