INDEX

Explanations

words related to assessments, evaluations and appraisals

oai_token-act-pair · gpt-3.5-turbo

terms related to assessment and evaluation processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

feeding

-0.77

vous

-0.72

seed

-0.71

die

-0.67

cat

-0.67

cop

-0.67

mpeg

-0.66

Else

-0.66

fing

-0.65

driver

-0.65

POSITIVE LOGITS

 appraisal

0.94

 assessment

0.84

oice

0.84

 assessing

0.83

itatively

0.83

 assessments

0.83

ments

0.81

 assess

0.80

essment

0.78

ablishment

0.77

Activations Density 0.025%

words related to assessments, evaluations and appraisals

terms related to assessment and evaluation processes

No Comments

No Known Activations