INDEX

Explanations

words related to legal issues and investigations

oai_token-act-pair · gpt-3.5-turbo

discussion surrounding issues of consequence or serious matters

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

 Gamble

-0.63

 Dress

-0.55

 wheelchair

-0.54

 dress

-0.54

ictive

-0.54

[+

-0.53

 Able

-0.52

 Vers

-0.52

Lv

-0.51

 disliked

-0.51

POSITIVE LOGITS

etheless

0.90

]).

0.81

`.

0.70

].

0.67

*.

0.67

.).

0.67

 sqor

0.67

+.

0.66

]."

0.66

''.

0.65

Activations Density 2.573%

words related to legal issues and investigations

discussion surrounding issues of consequence or serious matters

No Comments

No Known Activations