INDEX

Explanations

mentions of medical conditions related to hyperactivity, particularly focusing on 'kin'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "kin" in various contexts

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

 Seym

-0.96

enance

-0.74

reon

-0.73

 cryst

-0.71

eas

-0.71

Ö¼

-0.70

ffic

-0.68

inance

-0.65

ained

-0.61

eredith

-0.61

POSITIVE LOGITS

etics

1.23

etic

1.16

ning

1.14

etically

1.12

ners

1.04

ny

1.03

ned

1.03

esthetic

1.01

ifest

0.92

wagen

0.90

Activations Density 0.015%

mentions of medical conditions related to hyperactivity, particularly focusing on 'kin'

occurrences of the word "kin" in various contexts

No Comments

No Known Activations