INDEX

Explanations

words related to the aftermath or consequences of an event

oai_token-act-pair · gpt-3.5-turbo

keywords associated with post-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

amiya

-0.66

irlf

-0.64

 Rivals

-0.61

ONSORED

-0.59

steen

-0.59

PASS

-0.58

onga

-0.56

 Borg

-0.56

Known

-0.55

 Aman

-0.55

POSITIVE LOGITS

umatic

0.95

opausal

0.89

ocalyptic

0.82

ariat

0.80

ension

0.77

urchase

0.77

lict

0.76

roleum

0.75

liction

0.74

ITION

0.73

Activations Density 0.107%

words related to the aftermath or consequences of an event

keywords associated with post-related concepts

No Comments

No Known Activations