INDEX

Explanations

terms related to analysis, critique, and evaluating different situations

oai_token-act-pair · gpt-3.5-turbo

discussions related to effects and outcomes of actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Leilan

-0.57

ahime

-0.55

 Indra

-0.55

rition

-0.54

allery

-0.53

ipel

-0.52

 understatement

-0.52

 confir

-0.52

 Quan

-0.51

 Canaan

-0.51

POSITIVE LOGITS

}}

0.69

})

0.64

 exists

0.62

})

0.61

 cannot

0.60

)]

0.60

 hadn

0.57

 couldn

0.57

 might

0.57

]]

0.56

Activations Density 1.508%

terms related to analysis, critique, and evaluating different situations

discussions related to effects and outcomes of actions

No Comments

No Known Activations