INDEX

Explanations

dates in specific formats

oai_token-act-pair · gpt-3.5-turbo

dates and temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

etheless

-0.65

ktop

-0.65

anium

-0.64

rouse

-0.61

ebook

-0.61

hyde

-0.58

venge

-0.57

 endif

-0.57

channelAvailability

-0.56

want

-0.55

POSITIVE LOGITS

0.83

0.82

0.81

0.79

0.77

0.76

Activations Density 0.095%

dates in specific formats

dates and temporal references

No Comments

No Known Activations