INDEX

Explanations

words related to medical conditions, specifically focusing on "elastic" and "ACL"

oai_token-act-pair · gpt-3.5-turbo

terms related to elasticity and knee injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

erers

-0.71

yah

-0.69

erer

-0.68

 Guid

-0.67

acht

-0.67

acca

-0.64

ochet

-0.64

ploma

-0.64

namese

-0.62

ribution

-0.62

POSITIVE LOGITS

 unden

0.83

search

0.79

 streng

0.76

pse

0.76

 traged

0.73

ternity

0.69

 livest

0.69

omorphic

0.68

enaries

0.68

sie

0.68

Activations Density 0.020%

words related to medical conditions, specifically focusing on "elastic" and "ACL"

terms related to elasticity and knee injuries

No Comments

No Known Activations