INDEX

Explanations

medical and clinical terms and contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "clinical" in various contexts related to medical and psychological practice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĥĺ

-0.75

estamp

-0.71

Dick

-0.71

atto

-0.70

heads

-0.69

Wan

-0.68

atron

-0.68

 Grayson

-0.68

 Kinnikuman

-0.68

gat

-0.66

POSITIVE LOGITS

 trials

1.19

 trial

1.01

 Trials

1.00

tri

0.96

 evaluations

0.96

Tri

0.94

ising

0.93

ization

0.89

 evaluation

0.88

 examination

0.88

Activations Density 0.040%

medical and clinical terms and contexts

occurrences of the term "clinical" in various contexts related to medical and psychological practice

No Comments

No Known Activations