INDEX

Explanations

statements related to the level of trust or lack of trust in various entities or systems

oai_token-act-pair · gpt-3.5-turbo

phrases related to trust and confidence in institutions and authority figures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥķãĤ©

-0.82

netflix

-0.81

ycle

-0.73

imilar

-0.73

ozo

-0.71

selage

-0.70

pain

-0.70

ãĥ¼ãĥĨãĤ£

-0.69

furt

-0.68

traumatic

-0.67

POSITIVE LOGITS

worthiness

1.05

 judgment

0.95

 assurance

0.93

 judgement

0.90

 sincerity

0.88

 trusting

0.84

 integrity

0.82

 authority

0.78

 confidence

0.78

 credibility

0.77

Activations Density 0.252%

statements related to the level of trust or lack of trust in various entities or systems

phrases related to trust and confidence in institutions and authority figures

No Comments

No Known Activations