INDEX

Explanations

names of people or characters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and last names of individuals

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

ãĥķãĤ¡

-0.72

chest

-0.70

ãĥ¬

-0.66

Îº

-0.64

establishment

-0.61

ãĥĳ

-0.61

higher

-0.60

¡

-0.58

ĭ

-0.58

¦

-0.58

POSITIVE LOGITS

 also

1.06

 furthermore

0.93

 admits

0.90

 therefore

0.90

 appealed

0.88

 additionally

0.86

 remembers

0.86

 acknowledges

0.86

 believes

0.85

 however

0.85

Activations Density 0.285%

names of people or characters

proper nouns, specifically names and last names of individuals

No Comments

No Known Activations