INDEX

Explanations

words related to "pernicious" or names that start with "Per-", along with some terms related to medical conditions

oai_token-act-pair · gpt-3.5-turbo

topics related to deception or negative connotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bley

-0.72

inki

-0.67

bane

-0.63

ĸļ

-0.62

Introduced

-0.61

DAQ

-0.59

usercontent

-0.58

Joy

-0.58

nuts

-0.58

byn

-0.57

POSITIVE LOGITS

ctory

1.04

cia

0.85

etric

0.85

icular

0.78

haps

0.78

ulture

0.77

ulum

0.73

reau

0.73

emn

0.71

neau

0.71

Activations Density 0.044%

words related to "pernicious" or names that start with "Per-", along with some terms related to medical conditions

topics related to deception or negative connotations

No Comments

No Known Activations