INDEX

Explanations

words related to press secretaries

oai_token-act-pair · gpt-3.5-turbo

references to press secretaries and related roles in the context of government communications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abbage

-0.78

interest

-0.77

paying

-0.72

vasive

-0.72

liga

-0.71

esm

-0.69

urious

-0.68

[|

-0.67

UCT

-0.65

avascript

-0.65

POSITIVE LOGITS

Ari

0.82

 Betsy

0.75

Anne

0.73

 Sean

0.72

 Katie

0.72

 aide

0.71

 Suzanne

0.70

CTR

0.68

 Ernst

0.68

 Emails

0.67

Activations Density 0.079%

words related to press secretaries

references to press secretaries and related roles in the context of government communications

No Comments

No Known Activations