INDEX

Explanations

dates and time periods

oai_token-act-pair · gpt-3.5-turbo

references to specific historical time periods and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

malink

-0.91

Score

-0.69

ticket

-0.69

Sensor

-0.66

NESS

-0.66

Plug

-0.65

otine

-0.65

iken

-0.64

Storage

-0.64

vec

-0.64

POSITIVE LOGITS

 onwards

1.32

 onward

1.11

BCE

1.05

Era

0.99

 timeframe

0.83

era

0.82

ixties

0.81

CE

0.76

 Ferdinand

0.75

Activations Density 0.138%

dates and time periods

references to specific historical time periods and events

No Comments

No Known Activations