INDEX

Explanations

references to durations of time, particularly emphasizing the concept of years

oai_token-act-pair · gpt-3.5-turbo

mentions of "years" and time intervals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 contag

-0.70

agonist

-0.69

iqu

-0.66

amina

-0.63

emort

-0.61

artments

-0.60

Exit

-0.59

anooga

-0.59

 Plane

-0.59

ioch

-0.59

POSITIVE LOGITS

ago

1.21

Ago

1.05

mith

0.77

long

0.75

oming

0.74

ä¹

0.71

manship

0.71

lasting

0.71

 longer

0.69

 elapsed

0.68

Activations Density 0.125%

references to durations of time, particularly emphasizing the concept of years

mentions of "years" and time intervals

No Comments

No Known Activations