INDEX

Explanations

phrases related to communication or getting in touch with others

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 preceded

-0.82

 followed

-0.68

 namely

-0.68

ingu

-0.65

 apart

-0.64

 rever

-0.62

 according

-0.61

 besides

-0.61

 surely

-0.61

perm

-0.61

POSITIVE LOGITS

 same

0.95

 Clintons

0.95

 aforementioned

0.95

 wearer

0.93

resa

0.93

 nation

0.92

 fullest

0.91

 entire

0.91

 highest

0.90

 likes

0.90

Activations Density 0.723%

phrases related to communication or getting in touch with others

occurrences of the word "the"

No Comments

No Known Activations