INDEX

Explanations

scientific or medical findings and reports

oai_token-act-pair · gpt-3.5-turbo

verbs related to documentation and reporting of observations or findings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pin

-0.66

awk

-0.63

oyal

-0.62

fin

-0.61

 patience

-0.61

ospel

-0.61

 humble

-0.60

pat

-0.60

cop

-0.59

rest

-0.59

POSITIVE LOGITS

ãĥ¼ãĥĨ

0.78

 psychiat

0.77

 clinically

0.76

 anecd

0.74

 Parenthood

0.73

Obj

0.72

 Qiao

0.71

enz

0.70

 elsewhere

0.70

UD

0.70

Activations Density 0.174%

scientific or medical findings and reports

verbs related to documentation and reporting of observations or findings

No Comments

No Known Activations