INDEX

Explanations

phrases related to ongoing events or situations

oai_token-act-pair · gpt-3.5-turbo

occurrences and continuity of events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ritical

-0.81

claimer

-0.63

abre

-0.60

anity

-0.60

quickShipAvailable

-0.60

atta

-0.58

correct

-0.56

sharp

-0.56

rition

-0.56

having

-0.56

POSITIVE LOGITS

 around

1.07

 nowadays

0.94

 elsewhere

0.93

 abroad

0.93

 globally

0.91

 across

0.89

 concurrently

0.89

 lately

0.88

 worldwide

0.87

 throughout

0.82

Activations Density 0.310%

phrases related to ongoing events or situations

occurrences and continuity of events or actions

No Comments

No Known Activations