INDEX

Explanations

phrases related to conducting experiments or evaluations

oai_token-act-pair · gpt-3.5-turbo

references to testing or evaluations of various subjects or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Deaths

-0.79

displayText

-0.76

\">

-0.75

lance

-0.72

CHAPTER

-0.70

Â¨

-0.67

externalActionCode

-0.62

SOURCE

-0.60

enza

-0.60

anza

-0.59

POSITIVE LOGITS

 hypotheses

1.12

 viability

0.92

 feasibility

0.92

 readiness

0.91

 hypothesis

0.91

worthiness

0.91

 validity

0.76

 correctness

0.74

 effectiveness

0.72

 efficacy

0.72

Activations Density 0.216%

phrases related to conducting experiments or evaluations

references to testing or evaluations of various subjects or objects

No Comments

No Known Activations