INDEX

Explanations

numerical quantities followed by units of measurement

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "approximately."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

woods

-0.78

ters

-0.77

era

-0.76

ny

-0.73

lined

-0.72

ieu

-0.70

ned

-0.68

neys

-0.66

jit

-0.66

enders

-0.65

POSITIVE LOGITS

0.81

0.76

0.75

 âĸĪ

0.74

Activations Density 0.017%

numerical quantities followed by units of measurement

occurrences of the word "approximately."

No Comments

No Known Activations