INDEX

Explanations

references to events, situations, or objects that are described as massive or huge

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "massive" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

yer

-0.89

say

-0.74

keeper

-0.73

wich

-0.72

keepers

-0.71

nery

-0.71

wick

-0.70

men

-0.69

©¶æ

-0.69

nob

-0.69

POSITIVE LOGITS

 amounts

1.12

 earthqu

0.93

 undertaking

0.93

 influx

0.91

 quantities

0.91

 scale

0.88

 swath

0.83

 proportions

0.82

 amount

0.82

achusetts

0.81

Activations Density 0.035%

references to events, situations, or objects that are described as massive or huge

occurrences of the word "massive" in various contexts

No Comments

No Known Activations