INDEX

Explanations

words related to communication or reporting, specifically the word "said"

oai_token-act-pair · gpt-3.5-turbo

spoken dialogue or quotations

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

ntil

-0.70

Ranked

-0.70

pleting

-0.68

OSS

-0.66

ghazi

-0.66

VPN

-0.65

redo

-0.65

²¾

-0.64

ading

-0.64

prus

-0.64

POSITIVE LOGITS

 goodbye

0.97

 aloud

0.87

sonian

0.80

escription

0.76

 sarcast

0.75

 earlier

0.70

Origin

0.68

 hello

0.66

 publicly

0.65

bye

0.65

Activations Density 0.089%

words related to communication or reporting, specifically the word "said"

spoken dialogue or quotations

No Comments

No Known Activations