INDEX

Explanations

quantitative information related to time periods

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate time periods or sequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.84

ÙĲ

-0.69

rals

-0.66

thren

-0.65

ographical

-0.64

gor

-0.63

olog

-0.62

ologies

-0.61

Items

-0.60

onne

-0.59

POSITIVE LOGITS

 existence

0.87

 gestation

0.86

 campaigning

0.82

imester

0.81

 Ramadan

0.81

 tenancy

0.78

 occupancy

0.78

 hostilities

0.73

 adolescence

0.73

 eligibility

0.73

Activations Density 0.073%

quantitative information related to time periods

phrases that indicate time periods or sequences

No Comments

No Known Activations