INDEX

Explanations

phrases mentioning specific time periods, specifically "years."

oai_token-act-pair · gpt-3.5-turbo

references to specific time periods or durations

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

 bluff

-0.76

 Hunts

-0.65

 barg

-0.59

 sleeper

-0.58

IPP

-0.57

Mat

-0.57

urn

-0.54

 swords

-0.53

 Desk

-0.53

 burial

-0.53

POSITIVE LOGITS

 anniversary

0.80

imester

0.77

ynski

0.77

ĸļ

0.74

iott

0.73

ago

0.72

tml

0.70

cia

0.69

âĢ²

0.69

orate

0.69

Activations Density 0.068%

phrases mentioning specific time periods, specifically "years."

references to specific time periods or durations

No Comments

No Known Activations