INDEX

Explanations

words related to support or help

oai_token-act-pair · gpt-3.5-turbo

features related to characteristics of individuals or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

.</

-0.82

—

-0.77

.?

-0.76

.''.

-0.76

.—

-0.73

.[

-0.71

 âĢķ

-0.71

-0.70

âĢł

-0.70

*.

-0.69

POSITIVE LOGITS

 however

0.94

tho

0.78

 meanwhile

0.77

 alot

0.72

 organise

0.70

 though

0.69

 realise

0.64

 organising

0.63

anwhile

0.63

 learnt

0.60

Activations Density 1.589%

words related to support or help

features related to characteristics of individuals or identity

No Comments

No Known Activations