INDEX

Explanations

terms related to different teams within a company, particularly development and security teams

oai_token-act-pair · gpt-3.5-turbo

references to teams and groups involved in projects or work

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

ãĥ´

-0.86

ãĤ¤ãĥĪ

-0.75

Ô

-0.75

pload

-0.74

ãĥĸ

-0.72

çĭ

-0.71

anyl

-0.71

ministic

-0.71

":"/

-0.71

ãĤ¨ãĥ«

-0.70

POSITIVE LOGITS

 extraord

0.97

 hired

0.83

 accredited

0.76

 certified

0.76

ateurs

0.73

 specializing

0.72

 Panasonic

0.72

esses

0.71

 Gleaming

0.70

 Giul

0.68

Activations Density 0.308%

terms related to different teams within a company, particularly development and security teams

references to teams and groups involved in projects or work

No Comments

No Known Activations