INDEX

Explanations

instances where trust or lack of trust is mentioned

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to trust and belief in others

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

ciation

-0.85

que

-0.77

ãĥĩãĤ£

-0.76

 disadvantage

-0.73

ãĥ¼ãĥĨãĤ£

-0.73

atto

-0.72

aka

-0.71

eteenth

-0.69

ktop

-0.68

irable

-0.68

POSITIVE LOGITS

worthiness

1.16

 judgement

1.06

 judgment

0.99

 reliability

0.97

 authority

0.97

 trusting

0.97

 instincts

0.96

 integrity

0.96

 trustworthy

0.94

 sincerity

0.93

Activations Density 0.176%

instances where trust or lack of trust is mentioned

words and phrases related to trust and belief in others

No Comments

No Known Activations