INDEX

Explanations

phrases related to news events and incidents

oai_token-act-pair · gpt-3.5-turbo

occurrences of commas in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ocl

-0.82

ction

-0.76

estones

-0.69

onym

-0.69

cel

-0.67

matically

-0.66

itialized

-0.65

ety

-0.64

erv

-0.63

uten

-0.63

POSITIVE LOGITS

 according

0.98

 respectively

0.92

 including

0.91

 thereby

0.88

 prompting

0.86

SPONSORED

0.83

 namely

0.83

 citing

0.83

 albeit

0.82

ItemTracker

0.80

Activations Density 0.937%

phrases related to news events and incidents

occurrences of commas in the text

No Comments

No Known Activations