INDEX

Explanations

words related to interruptions or disturbances

oai_token-act-pair · gpt-3.5-turbo

terms related to disruption and its effects 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rouse

-0.79

tre

-0.78

onz

-0.78

ric

-0.76

cop

-0.73

reed

-0.72

vet

-0.70

swick

-0.70

nda

-0.70

reth

-0.70

POSITIVE LOGITS

 disruption

1.10

 disruptions

1.10

 interruption

1.09

 havoc

0.90

 disrupted

0.89

 inconven

0.86

 disrupt

0.84

 outage

0.83

 interrupt

0.82

 disrupting

0.80

Activations Density 0.014%

words related to interruptions or disturbances

terms related to disruption and its effects in various contexts

No Comments

No Known Activations