INDEX

Explanations

words related to difficulties or challenges

oai_token-act-pair · gpt-3.5-turbo

terms related to difficulty or challenges experienced by individuals

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

isite

-0.73

TION

-0.68

ortium

-0.66

imental

-0.64

ement

-0.64

aceae

-0.61

Bone

-0.60

MIT

-0.60

ENCE

-0.59

umes

-0.58

POSITIVE LOGITS

 navigating

1.20

 figuring

1.20

 adapting

1.20

 finding

1.19

 locating

1.15

 adjusting

1.15

 integrating

1.12

 getting

1.12

 distinguishing

1.08

 convincing

1.08

Activations Density 0.110%

words related to difficulties or challenges

terms related to difficulty or challenges experienced by individuals

No Comments

No Known Activations