INDEX

Explanations

phrases related to questioning or confirming the trustworthiness or accuracy of something

oai_token-act-pair · gpt-3.5-turbo

references to the concept of credibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Shop

-0.76

hib

-0.75

sets

-0.74

xon

-0.73

opa

-0.72

mare

-0.70

EMS

-0.67

hire

-0.66

sg

-0.66

oval

-0.66

POSITIVE LOGITS

 credibility

1.17

 legitimacy

0.99

ibly

0.94

 credentials

0.91

 tremend

0.89

worthiness

0.84

 clout

0.80

 guiActiveUn

0.79

 multiplier

0.76

 proposition

0.75

Activations Density 0.009%

phrases related to questioning or confirming the trustworthiness or accuracy of something

references to the concept of credibility

No Comments

No Known Activations